# io.github.tang-vu/keryx: tool descriptions scored

- tools/list taken: 2026-11-02 (UTC)
- From: [Official MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.tang-vu%2Fkeryx/versions/latest)
- Connected to: https://keryx.cc/mcp
- Homepage: https://keryx.cc/
- Repository: https://github.com/tang-vu/keryx
- Scoring rules: v2
- Tools: 27
- Average: 50.7 / 100 (Cloudy)
- Near-identical pairs: 7

This page shows how io.github.tang-vu/keryx'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

- Minor: 27 tools. Above 25, models start to tell tools apart less well.
- Critical: These tools share the same description: research_feedback_read, research_feedback_submit.
- Critical: These tools share the same description: history_owned_read, history_export.
- Critical: These tools share the same description: history_private_jobs_list, history_private_jobs_detail.
- Critical: These tools share the same description: run_privacy_read, run_owner_export.
- Minor: The server has no instructions. Say there, once, what the server is for and when to use it: Claude Code and Gemini CLI read the instructions before the tool descriptions.

## Tools

- `keryx_source_learning`: 37 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: sourceId.
  - Minor: Says nothing about what it returns.
  - Minor: Required identifiers whose description does not say where the value comes from: sourceId. Name the tool or the place that returns it, or models look it up first.
- `history_read`: 39 / 100
  - Major: Arguments without a description: limit, cursor, search, surface, funding, from, to.
  - Minor: No `required` list, so every argument is optional.
  - Minor: Says nothing about what it returns.
- `run_owner_export`: 39 / 100
  - Major: Arguments without a description: id, requestId.
  - Minor: Says nothing about what it returns.
  - Minor: Required identifiers whose description does not say where the value comes from: id, requestId. Name the tool or the place that returns it, or models look it up first.
- `run_privacy_read`: 39 / 100
  - Major: Arguments without a description: id.
  - Minor: Says nothing about what it returns.
  - Minor: Required identifiers whose description does not say where the value comes from: id. Name the tool or the place that returns it, or models look it up first.
- `history_private_jobs_list`: 42 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: limit, cursor, search, surface, network, from, to.
  - Minor: No `required` list, so every argument is optional.
  - Minor: The description mentions none of its 3 or more arguments.
- `keryx_public_job_ledger`: 42 / 100
  - Major: Arguments without a description: days.
  - Minor: No `required` list, so every argument is optional.
  - Minor: Says nothing about what it returns.
- `profile_update`: 44 / 100
  - Major: Arguments without a description: profile.displayName, profile.handle, profile.bio, profile.purpose, profile.links, profile.links[].kind, profile.links[].url.
  - Minor: Says nothing about what it returns.
- `deliverable_acceptance_submit`: 45 / 100
  - Major: Arguments without a description: id, submission, submission.originalFingerprint, submission.deliveredDigest, submission.expectedRevision, submission.idempotencyKey, submission.choice, submission.reason, submission.publishState.
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: The meaning of the boolean argument submission.publishState is unclear.
  - Minor: Says nothing about what it returns.
  - Minor: Required identifiers whose description does not say where the value comes from: id. Name the tool or the place that returns it, or models look it up first.
- `history_private_jobs_detail`: 45 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: id.
  - Minor: Required identifiers whose description does not say where the value comes from: id. Name the tool or the place that returns it, or models look it up first.
- `deliverable_acceptance_read`: 46 / 100
  - Major: Arguments without a description: id.
  - Minor: Required identifiers whose description does not say where the value comes from: id. Name the tool or the place that returns it, or models look it up first.
- `evidence_draft`: 49 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: No `required` list, so every argument is optional.
  - Minor: Says nothing about what it returns.
- `history_private_jobs_export`: 49 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: limit, cursor, search, surface, network, from, to.
  - Minor: No `required` list, so every argument is optional.
  - Minor: The description mentions none of its 3 or more arguments.
- `keryx_status`: 49 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Says nothing about what it returns.
- `history_export`: 52 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Says nothing about what it returns.
- `history_owned_read`: 52 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Says nothing about what it returns.
- `keryx_operator_status`: 52 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Says nothing about what it returns.
- `keryx_purchase_outcomes`: 52 / 100
  - Major: Arguments without a description: dispatchId.
  - Minor: Required identifiers whose description does not say where the value comes from: dispatchId. Name the tool or the place that returns it, or models look it up first.
- `evidence_procurement`: 54 / 100
  - Minor: No `required` list, so every argument is optional.
  - Minor: Says nothing about what it returns.
- `profile_read`: 54 / 100
  - Minor: Says nothing about what it returns.
- `research_monthly`: 54 / 100
  - Minor: Says nothing about what it returns.
- `operator_obligations_read`: 55 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Says nothing about what it returns.
- `draft_check`: 57 / 100
  - Minor: No `required` list, so every argument is optional.
  - Minor: Says nothing about what it returns.
- `profile_identities_read`: 60 / 100
  - Minor: Says nothing about what it returns.
- `research`: 60 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Arguments without a description: researchMode, responseMode.
- `research_feedback_submit`: 62 / 100
  - Major: Arguments without a description: choice, reason.
- `paper_lookup`: 67 / 100
- `research_feedback_read`: 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)