# NOT FOR HUMANS (io.github.notforhumansfun-rgb/not-for-humans): tool descriptions scored

- tools/list taken: 2026-11-02 (UTC)
- From: [Official MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.notforhumansfun-rgb%2Fnot-for-humans/versions/latest)
- Connected to: https://mcp.notforhumans.fun/mcp
- Homepage: https://notforhumans.fun/
- Repository: https://github.com/notforhumansfun-rgb/not-for-humans-mcp
- Scoring rules: v2
- Tools: 69
- Average: 57.3 / 100 (Cloudy)
- Near-identical pairs: 3

This page shows how NOT FOR HUMANS (io.github.notforhumansfun-rgb/not-for-humans)'s tool descriptions scored, the issues found and the names of its tools and parameters. The descriptions are the server's own: read them where the copy came from.

Forecall asked the URL this server lists in the official MCP Registry for its tools/list once, on the date above, without calling any tool. The server may have changed since.

## Across the server

- Major: 69 tools. Above 40, models choose less accurately.

## Tools

- `list_returned_work`: 39 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: limit, requestId.
  - Minor: No `required` list, so every argument is optional.
- `list_accepted_work`: 42 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: limit.
  - Minor: No `required` list, so every argument is optional.
- `list_agent_requests`: 42 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: limit.
  - Minor: No `required` list, so every argument is optional.
- `list_arcade_lobby`: 44 / 100
  - Major: Arguments without a description: limit.
  - Minor: No `required` list, so every argument is optional.
- `get_agent_entry`: 47 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Arguments without a description: reservationId.
  - Minor: No `required` list, so every argument is optional.
- `prepare_accepted_work`: 49 / 100
  - Major: Arguments without a description: learning, learning.approach, learning.feedback, learning.lesson, learning.proposedSkill, learning.proposedSkill.name, learning.proposedSkill.scope, learning.proposedSkill.instructions, learning.proposedSkill.testPlan.
  - Minor: Required identifiers whose description does not say where the value comes from: requestId, workerTokenId. Name the tool or the place that returns it, or models look it up first.
- `prepare_tasq_principal_binding`: 49 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Arguments without a description: transport.kind, transport.id.
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId, spaceId, tasqPrincipalId. Name the tool or the place that returns it, or models look it up first.
- `list_active_agents`: 50 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Arguments without a description: limit.
  - Minor: No `required` list, so every argument is optional.
- `prepare_agent_request`: 50 / 100
  - Major: Arguments without a description: constraints, compensation, missionKind, maxAgents, rewardType, rewardAmount, rewardCurrency, expiresInHours.
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `prepare_internal_cancel_listing`: 50 / 100
  - Major: The description is too short (7 words).
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `prepare_internal_cancel_offer`: 50 / 100
  - Major: The description is too short (7 words).
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `get_agent_pfp`: 52 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Arguments without a description: transactionHash.
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `get_arcade_player_status`: 53 / 100
  - Major: Says nothing about when to use it, or when not to.
- `list_agent_learning_receipts`: 53 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Arguments without a description: limit.
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `prepare_agent_presence_delegation`: 53 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Arguments without a description: validForHours.
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `enter_signal_city`: 54 / 100
  - Major: Says nothing about when to use it, or when not to.
- `list_trait_offers`: 54 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Arguments without a description: limit.
- `prepare_agent_entry`: 54 / 100
  - Major: Says nothing about when to use it, or when not to.
- `prepare_agent_entry_activity`: 54 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Required identifiers whose description does not say where the value comes from: reservationId. Name the tool or the place that returns it, or models look it up first.
- `prepare_agent_learning_decision`: 54 / 100
  - Minor: Arguments without a description: tests[].name, tests[].evidenceHash, tests[].passed.
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: The meaning of the boolean argument tests[].passed is unclear.
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId, proposalId. Name the tool or the place that returns it, or models look it up first.
- `prepare_agent_presence`: 54 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `prepare_internal_buy`: 54 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `prepare_internal_listing`: 54 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `prepare_internal_offer`: 54 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `watch_signal_city`: 54 / 100
  - Major: Says nothing about when to use it, or when not to.
- `get_arcade_match`: 56 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Required identifiers whose description does not say where the value comes from: matchId. Name the tool or the place that returns it, or models look it up first.
- `prepare_census_receipt`: 56 / 100
  - Minor: Arguments without a description: reasonHash, publicStatement.
  - Minor: The description mentions none of its 3 or more arguments.
- `activate_agent_entry`: 57 / 100
  - Major: Says nothing about when to use it, or when not to.
- `get_census_status`: 57 / 100
  - Major: Says nothing about when to use it, or when not to.
- `get_mainnet_marketplace_status`: 57 / 100
  - Major: Says nothing about when to use it, or when not to.
- `get_market_status`: 57 / 100
  - Major: Says nothing about when to use it, or when not to.
- `get_origin_stream`: 57 / 100
  - Major: Says nothing about when to use it, or when not to.
- `get_tokenworks_status`: 57 / 100
  - Major: Says nothing about when to use it, or when not to.
- `join_arcade_game`: 57 / 100
  - Major: Says nothing about when to use it, or when not to.
- `prepare_agent_skill_rollback`: 57 / 100
  - Minor: Arguments without a description: tests[].name, tests[].evidenceHash, tests[].passed.
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: The meaning of the boolean argument tests[].passed is unclear.
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `prepare_internal_accept_offer`: 57 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `prepare_public_claim`: 57 / 100
  - Minor: Arguments without a description: publicStatement.
  - Minor: The description mentions none of its 3 or more arguments.
- `prepare_trait_offer`: 57 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Arguments without a description: startTime.
- `search`: 57 / 100
  - Major: Says nothing about when to use it, or when not to.
- `submit_agent_entry_activity`: 57 / 100
  - Major: Says nothing about when to use it, or when not to.
- `prepare_accept_offer`: 59 / 100
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `prepare_arcade_session`: 59 / 100
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `prepare_delegated_agent_heartbeat`: 59 / 100
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `prepare_purchase`: 59 / 100
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `prepare_returned_work`: 59 / 100
  - Minor: Required identifiers whose description does not say where the value comes from: requestId, workerTokenId. Name the tool or the place that returns it, or models look it up first.
- `prepare_transfer`: 59 / 100
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `fetch`: 60 / 100
  - Major: Says nothing about when to use it, or when not to.
- `get_agent_public_brain`: 60 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `play_arcade_move`: 60 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: Required identifiers whose description does not say where the value comes from: matchId. Name the tool or the place that returns it, or models look it up first.
- `play_signal_city`: 60 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: The description mentions none of its 3 or more arguments.
- `prepare_listing`: 61 / 100
  - Minor: Arguments without a description: startTime.
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `prepare_tokenworks_decision`: 61 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `get_agent_entry_status`: 62 / 100
- `get_agent_wallet_onboarding`: 62 / 100
- `get_internal_marketplace_status`: 62 / 100
- `reconcile_agent_entry_claim`: 62 / 100
  - Minor: Required identifiers whose description does not say where the value comes from: reservationId. Name the tool or the place that returns it, or models look it up first.
- `get_market_feed`: 65 / 100
- `get_tasq_principal_binding`: 65 / 100
  - Minor: Arguments without a description: transport.kind, transport.id.
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId, spaceId, tasqPrincipalId. Name the tool or the place that returns it, or models look it up first.
- `prepare_mainnet_buy`: 66 / 100
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `prepare_mainnet_cancel_listing`: 66 / 100
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `prepare_mainnet_cancel_offer`: 66 / 100
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `prepare_mainnet_listing`: 66 / 100
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `prepare_mainnet_offer`: 66 / 100
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `get_agent_identity_bootstrap`: 67 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `claim_as_agent`: 69 / 100
- `find_best_order`: 69 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `get_agent_next_action`: 69 / 100
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `prepare_mainnet_accept_offer`: 69 / 100
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: Required identifiers whose description does not say where the value comes from: tokenId. Name the tool or the place that returns it, or models look it up first.
- `prepare_agent_entry_claim`: 72 / 100

Is your server listed here and you would rather it were not? Email support@forecall.dev, and we will take it off within 7 days.

[All scored servers](https://forecall.dev/en/servers)