# Santismm Knowledge — Harness Engineering, Agentic AI & Governance (com.santismm/knowledge): tool descriptions scored

- tools/list taken: 2026-11-02 (UTC)
- From: [Official MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/com.santismm%2Fknowledge/versions/latest)
- Connected to: https://santismm.com/mcp
- Homepage: https://santismm.com/en/mcp
- Repository: https://github.com/santismm/santismm-knowledge-mcp
- Scoring rules: v2
- Tools: 36
- Average: 71.3 / 100 (Clear)
- Near-identical pairs: 0

This page shows how Santismm Knowledge — Harness Engineering, Agentic AI & Governance (com.santismm/knowledge)'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: 36 tools. Above 25, models start to tell tools apart less well.
- 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

- `list_claims`: 60 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: No `required` list, so every argument is optional.
- `list_homeric_routes`: 60 / 100
  - Minor: No `required` list, so every argument is optional.
- `list_benchmarks`: 65 / 100
  - Minor: No `required` list, so every argument is optional.
- `list_governance`: 65 / 100
  - Minor: No `required` list, so every argument is optional.
- `list_homeric_episodes`: 65 / 100
  - Minor: No `required` list, so every argument is optional.
- `list_homeric_places`: 65 / 100
  - Minor: No `required` list, so every argument is optional.
- `list_labs`: 65 / 100
  - Minor: No `required` list, so every argument is optional.
- `list_professions`: 65 / 100
  - Minor: No `required` list, so every argument is optional.
- `search`: 65 / 100
- `calculate_agent_economics`: 66 / 100
  - Minor: The description mentions none of its 3 or more arguments.
- `get_overview`: 67 / 100
  - Major: Says nothing about when to use it, or when not to.
- `calculate_human_supervision_capacity`: 68 / 100
  - Major: Says nothing about when to use it, or when not to.
- `get_governance`: 68 / 100
  - Major: Says nothing about when to use it, or when not to.
- `get_pattern`: 68 / 100
  - Major: Says nothing about when to use it, or when not to.
- `get_homeric_episode`: 70 / 100
- `get_homeric_place`: 70 / 100
- `get_homeric_route`: 70 / 100
- `list_patterns`: 70 / 100
  - Minor: No `required` list, so every argument is optional.
- `search_articles`: 70 / 100
  - Minor: The description mentions none of its 3 or more arguments.
- `get_architecture`: 71 / 100
  - Major: Says nothing about when to use it, or when not to.
- `calculate_evaluation_sample_size`: 73 / 100
- `get_article`: 73 / 100
- `get_benchmark`: 73 / 100
- `get_handbook`: 75 / 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: id. Name the tool or the place that returns it, or models look it up first.
- `get_knowledge`: 75 / 100
  - Major: Says nothing about when to use it, or when not to.
- `get_related`: 75 / 100
  - Minor: The description mentions none of its 3 or more arguments.
- `list_architectures`: 75 / 100
  - Minor: No `required` list, so every argument is optional.
- `list_articles`: 75 / 100
  - Minor: No `required` list, so every argument is optional.
- `list_handbook`: 75 / 100
  - Minor: No `required` list, so every argument is optional.
- `list_knowledge`: 75 / 100
  - Minor: No `required` list, so every argument is optional.
- `get_claim`: 77 / 100
  - 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.
- `get_lab`: 78 / 100
- `get_author_profile`: 80 / 100
- `compare_models`: 83 / 100
- `search_all`: 83 / 100
  - Minor: The description mentions none of its 3 or more arguments.
- `recommend_model_for_profession`: 90 / 100
  - 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.

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)