# Plumbline — a trust layer for LLM answers (com.lattice-sys.plumbline/mcp): tool descriptions scored

- tools/list taken: 2026-11-02 (UTC)
- From: [Official MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/com.lattice-sys.plumbline%2Fmcp/versions/latest)
- Connected to: https://plumbline.lattice-sys.com/mcp/demo
- Homepage: https://plumbline.lattice-sys.com/
- Scoring rules: v2
- Tools: 18
- Average: 69.7 / 100 (Cloudy)
- Near-identical pairs: 10

This page shows how Plumbline — a trust layer for LLM answers (com.lattice-sys.plumbline/mcp)'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: 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

- `ask_submit_draft`: 52 / 100
  - Major: Says nothing about when to use it, or when not to.
- `get_ai_act_transparency`: 64 / 100
  - Major: Says nothing about when to use it, or when not to.
- `ask_result`: 65 / 100
- `compare_departments`: 67 / 100
  - Minor: String arguments with no constraint or example: a, b.
- `get_manager_chain`: 67 / 100
- `search_employee`: 67 / 100
- `trust_finalize`: 67 / 100
  - Major: Says nothing about when to use it, or when not to.
- `run_sql`: 68 / 100
  - Major: Says nothing about when to use it, or when not to.
- `cross_check`: 69 / 100
  - Major: Says nothing about when to use it, or when not to.
- `find_payroll_anomalies`: 69 / 100
- `get_answer_queries`: 70 / 100
- `query_fact`: 70 / 100
  - Minor: Required identifiers whose description does not say where the value comes from: query_id. Name the tool or the place that returns it, or models look it up first.
- `run_code`: 70 / 100
  - Major: Says nothing about when to use it, or when not to.
- `search_docs`: 72 / 100
- `summarize_benefits`: 74 / 100
  - Minor: No `required` list, so every argument is optional.
- `get_evidence_document`: 75 / 100
  - Minor: Required identifiers whose description does not say where the value comes from: document_id. Name the tool or the place that returns it, or models look it up first.
- `describe_fact_capabilities`: 82 / 100
- `ask_prepare`: 87 / 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)