# TensorFeed (ai.tensorfeed/mcp-server): tool descriptions scored

- tools/list taken: 2026-11-02 (UTC)
- From: [Official MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/ai.tensorfeed%2Fmcp-server/versions/latest)
- Connected to: https://mcp.tensorfeed.ai/mcp
- Homepage: https://tensorfeed.ai/developers/agent-payments
- Repository: https://github.com/RipperMercs/tensorfeed-mcp
- Scoring rules: v2
- Tools: 30
- Average: 49.7 / 100 (Cloudy)
- Near-identical pairs: 0

This page shows how TensorFeed (ai.tensorfeed/mcp-server)'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: 30 tools. Above 25, models start to tell tools apart less well.
- Major: 15 tools repeat the same note (54 words). Say it once in the server's instructions, and let each description say what only that tool does. The note does not count toward the tools' scores.
- Minor: The server's instructions are 2353 characters. Claude Code reads only the first 2,048 by default (Codex 0.154.0 reads them whole). Put what the server is for first.

## Tools

- `search_sec_edgar`: 40 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: String arguments with no constraint or example: startdt, enddt.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `get_agent_opportunities`: 42 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: No `required` list, so every argument is optional.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `get_osv_advisory_for_package`: 42 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: String arguments with no constraint or example: name, version.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `compare_models`: 43 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Says nothing about what it returns.
  - Minor: Required identifiers whose description does not say where the value comes from: ids. Name the tool or the place that returns it, or models look it up first.
- `provider_deepdive`: 43 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Says nothing about what it returns.
- `get_epss_score`: 45 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
  - Minor: Required identifiers whose description does not say where the value comes from: cve_id. Name the tool or the place that returns it, or models look it up first.
- `get_models`: 45 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `get_cve_record`: 47 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
  - Minor: Required identifiers whose description does not say where the value comes from: cve_id. Name the tool or the place that returns it, or models look it up first.
- `get_kev_catalog`: 47 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: No `required` list, so every argument is optional.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `provider_reliability_verdict`: 47 / 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.
- `route_verdict`: 47 / 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.
- `status_leaderboard`: 47 / 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.
- `x402_settlement_verdict`: 48 / 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.
- `benchmark_series`: 49 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Says nothing about what it returns.
- `check_agent_reputation`: 49 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: No `required` list, so every argument is optional.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `get_news_articles`: 50 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: No `required` list, so every argument is optional.
- `get_research_papers`: 50 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `pricing_series`: 50 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Says nothing about what it returns.
- `status_uptime`: 50 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Says nothing about what it returns.
- `benchmark_trust_verdict`: 51 / 100
  - Minor: No `required` list, so every argument is optional.
  - Minor: Says nothing about what it returns.
  - Minor: The description says the tool is deprecated. Name the replacement, and consider taking the tool out of tools/list: models avoid it when asked for what it does.
- `submit_wantlist_item`: 52 / 100
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: Says nothing about what it returns.
- `check_ai_supply_chain_risk`: 55 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: No `required` list, so every argument is optional.
- `failover_verdict`: 55 / 100
  - Minor: Says nothing about what it returns.
- `get_status_summary`: 55 / 100
  - Major: Says nothing about when to use it, or when not to.
- `register_free_watch`: 55 / 100
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
  - Major: It may be destructive, but destructiveHint is not set.
- `ssvc_verdict`: 55 / 100
  - Minor: Says nothing about what it returns.
- `x402_publisher_verdict`: 55 / 100
  - Minor: Says nothing about what it returns.
- `whats_new`: 57 / 100
  - Minor: No `required` list, so every argument is optional.
- `find_tensorfeed_data`: 60 / 100
- `stack_safety_verdict`: 60 / 100
  - Minor: Says nothing about what it returns.

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)