Skip to main content
Glama
loomiomcp
by soil-dev

search_content

Read-onlyIdempotent

Search Loomio discussions, comments, polls, stances, and outcomes by keyword, author, group, or tag to find relevant content; results are capped at 20.

Instructions

Keyword search over everything the connector's user can see: 1 call. Pass query (prefix match; !word excludes), author_id alone for 'what did X post', or both. Hard cap: at most 20 results, no paging; capped: true means narrow the search. Stance hits on polls with hidden results are DROPPED from a query search; never use search to probe hidden vote reasons.

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": "search_content"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagNoOnly items tagged with this exact name (Loomio < 3.13: every item of a tagged thread).
orderNoauthored_at_desc (default), authored_at_asc, relevance.
queryNoFull-text query (prefix match; `!word` excludes).
typesNoRecord types to include; default all (e.g. ['Outcome']).
group_idNoRestrict to one group (not its subgroups).
author_idNoRestrict to one author; alone = their 20 newest items.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.0.17
    • addedInput schema / properties / query / maxLength
      Added value: +512
    • addedInput schema / properties / tag / maxLength
      Added value: +128
  2. Changed1 schema field changedv0.0.16
    • changedInput schema / properties / tag / description
      Previous value: -"Only threads carrying this tag (exact name)."New value: +"Only items tagged with this exact name (Loomio < 3.13: every item of a tagged thread)."
  3. Addedv0.0.13

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already cover the safety profile, yet the description adds real behavioral disclosure beyond them: a hard 20-result cap, no paging, the meaning of a returned 'capped: true' field, and the fact that stance hits on hidden-result polls are silently dropped. That is exactly the kind of non-obvious behavior an agent needs.

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

Conciseness5/5

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

Two dense sentences, front-loaded with the core scope, then usage patterns, then the hard cap caveat. No filler; every clause carries operational meaning.

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?

No output schema exists, and the description explains the meaningful returned field (capped). The filtering parameters (tag, order, types, group_id) are left entirely to the schema, which is acceptable given 100% coverage, but the description could hint that filters are available.

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, but the description adds value by clarifying how query and author_id compose ('or both') and that author_id alone returns the newest items — semantics an agent would otherwise have to infer from two separate field descriptions.

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?

States a specific verb and resource ('Keyword search over everything the connector's user can see') with a clear scope of one call. It doesn't explicitly name a sibling like list_discussions or get_thread_markdown as the alternative, so it stops short of full sibling differentiation.

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

Usage Guidelines4/5

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

Provides concrete invocation patterns ('Pass query... author_id alone for "what did X post", or both') and an explicit anti-use case ('never use search to probe hidden vote reasons'). It doesn't state when to prefer the paging list_* siblings, though the 'no paging' note implies it.

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