Skip to main content
Glama
loomiomcp
by soil-dev

get_thread_markdown

Read-onlyIdempotent

Reads a Loomio thread as server-rendered Markdown by topic, discussion, or poll ID, with optional character limits. Refuses requests when an open poll hides results until the user votes.

Instructions

The best single call for 'summarise / read this thread': 2 calls by topic_id, discussion_id or poll_id (pass exactly one; +1 per 500 items when the thread has replies) return Loomio's server-rendered Markdown (markdown, chars, truncated). REFUSED while an open poll hides results until the user votes: use list_thread_items. max_chars cuts the END: truncated: true = newest items dropped.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_thread_markdown"
  }
}

Input Schema

NameRequiredDescriptionDefault
poll_idNoPoll id or short key.
topic_idNoThread id (`topic_id` on any thread row, NOT `id`).
max_charsNoCap in chars; default 60000, -1 = all. Cuts the END; `truncated` flags it.
discussion_idNoDiscussion id or short key.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.0.17
    • changedInput schema / properties / discussion_id / anyOf
      Previous value: -[
      -  {
      -    "pattern": "^[A-Za-z0-9_-]+$",
      -    "type": "string"
      -  },
      -  {
      -    "exclusiveMinimum": 0,
      -    "maximum": 9007199254740991,
      -    "type": "integer"
      -  }
      -]New value: +[
      +  {
      +    "pattern": "^[A-Za-z0-9_-]{1,128}$",
      +    "type": "string"
      +  },
      +  {
      +    "exclusiveMinimum": 0,
      +    "maximum": 9007199254740991,
      +    "type": "integer"
      +  }
      +]
    • changedInput schema / properties / poll_id / anyOf
      Previous value: -[
      -  {
      -    "pattern": "^[A-Za-z0-9_-]+$",
      -    "type": "string"
      -  },
      -  {
      -    "exclusiveMinimum": 0,
      -    "maximum": 9007199254740991,
      -    "type": "integer"
      -  }
      -]New value: +[
      +  {
      +    "pattern": "^[A-Za-z0-9_-]{1,128}$",
      +    "type": "string"
      +  },
      +  {
      +    "exclusiveMinimum": 0,
      +    "maximum": 9007199254740991,
      +    "type": "integer"
      +  }
      +]
  2. Changed3 schema fields changedv0.0.16
    • changedInput schema / properties / discussion_id / description
      Previous value: -"Discussion id or short key (+1 call); prefer `topic_id`."New value: +"Discussion id or short key."
    • changedInput schema / properties / poll_id / description
      Previous value: -"Poll id or short key of a STANDALONE poll (+1 call)."New value: +"Poll id or short key."
    • changedInput schema / properties / topic_id / description
      Previous value: -"Thread id (`topic_id` on any thread row, NOT `id`); no extra call."New value: +"Thread id (`topic_id` on any thread row, NOT `id`)."
  3. Addedv0.0.13

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds substantial behavior beyond the readOnly/idempotent annotations: a call-cost model (2 calls, +1 per 500 replies), the open-poll refusal condition, and truncation semantics ('max_chars cuts the END; truncated: true = newest items dropped').

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then constraints, then return shape, with zero filler sentences. It is dense and heavy on backticked tokens, but each clause carries operative information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, yet the description names the returned fields (markdown, chars, truncated), explains refusal behavior, ID selection, and truncation — everything needed to call it correctly and interpret the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description adds real value by stating the mutual-exclusion rule ('pass exactly one') that the schema's empty required list does not enforce, and by explaining max_chars truncation direction.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('read this thread' returns server-rendered Markdown) and explicitly positions itself as the best single call for summarising/reading a thread, distinguishing it from list_thread_items, which is named for the refusal case.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says when to use it ('best single call for summarise / read this thread'), how to select the ID ('pass exactly one' of topic_id/discussion_id/poll_id), and names the alternative when it is refused (open poll hiding results → use list_thread_items).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.