Skip to main content
Glama
loomiomcp
by soil-dev

list_thread_items

Read-onlyIdempotent

Retrieve structured items from a Loomio thread by topic, discussion, or poll ID, with pagination and kind filtering, including referenced comments, polls, stances, outcomes, and users.

Instructions

One thread as structured items: 1 call per 500 items by topic_id (+1 by discussion_id or poll_id; pass exactly one). Returns items[] in thread order plus the comments, polls, stances (votes), outcomes and users they reference. Paged by limit / offset under the max_total_chars budget (kinds reads the whole thread); next_offset says where to continue.

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": "list_thread_items"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindsNoItem kinds to keep (e.g. new_comment, stance_created); 'other' = unlisted kinds.
limitNoItems after the kinds filter; default 200, max 1000.
offsetNoItems to skip. Default 0.
poll_idNoPoll id or short key (+1 call).
topic_idNoThread id (`topic_id` on any thread row, NOT `id`); no extra call.
strip_htmlNoPlain text instead of HTML bodies, reasons, outcomes; default true.
discussion_idNoDiscussion id or short key (+1 call); prefer `topic_id`.
body_max_charsNoChars per `body`; default 4000, 0 omits it, -1 = full.
max_total_charsNoReply budget in chars; default 120000, -1 = none. See next_offset.
include_reactionsNoAlso return emoji `reactions`. Default false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 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"
      +  }
      +]
    • addedInput schema / properties / kinds / items / maxLength
      Added value: +64
    • addedInput schema / properties / kinds / maxItems
      Added value: +32
    • 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. Changed1 schema field changedv0.0.16
    • 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 (+1 call)."
  3. Addedv0.0.13

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description earns credit for adding what annotations cannot: the call-cost model ('1 call per 500 items', +1 for discussion/poll ids), the `max_total_chars` budget interaction, and the `next_offset` continuation contract. It also warns that `kinds` reads the whole thread, a meaningful performance disclosure. It stops short of describing failure behavior for invalid id combinations.

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?

Dense but front-loaded: the return shape comes first, then the id-selection rule, then paging. Every clause carries information, though the heavy parenthetical/semicolon packing makes it slightly harder to scan than it needs to be.

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

Completeness4/5

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

For a 10-parameter, zero-required, no-output-schema read tool, the description is nearly complete: it covers return structure, paging, budget, truncation (`body_max_chars`), and continuation. The remaining gap is the underspecified 'exactly one id' requirement against a schema where no parameter is required.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents default/max values and even the '+1 call' costs that the description repeats. The description's only real addition is the note that `kinds` forces a whole-thread read and that paging happens under the `max_total_chars` budget — useful, but mostly restating the schema.

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

Purpose4/5

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

The description opens with a specific verb+resource framing: 'One thread as structured items', and clarifies the returned structure (`items[]` in thread order plus referenced comments, polls, stances, outcomes, users). This implicitly distinguishes it from get_thread_markdown, but it never names that sibling or list_threads, so the differentiation is left to inference.

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

Usage Guidelines3/5

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

It gives a concrete selection rule for the id parameters ('pass exactly one' of topic_id / discussion_id / poll_id) and notes the cost tradeoff (+1 call for the latter two), which is real usage guidance. However, it never says when to choose this tool over get_thread_markdown or list_threads, and it doesn't state what happens if zero or multiple ids are supplied despite none being required.

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