Skip to main content
Glama

Search a space's files

search_space_files
Read-onlyIdempotent

Find relevant passages across a space’s readings, slides, transcripts, and assignments by meaning or keywords; get snippets and locations to read only what you need.

Instructions

Search all of a space's files (readings, slides, transcripts, syllabus, assignments) by meaning and keywords. Returns the best passages, each with its id, file, place (page, slide, time or lines) and a short snippet. Open the ones you need with read_passage instead of reading whole files.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "space_id": "<space_id>",
      "query": "<query>"
    },
    "name": "search_space_files"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMost passages to return (default 8).
queryYesWhat to look for, in plain words.
space_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.1

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds value beyond that by describing the shape of the result (passages with id, file, place as page/slide/time/lines, and a short snippet) and the intended retrieval workflow, which the annotations cannot convey.

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 sentences, both earning their place: the first establishes scope and method, the second states the return shape and the follow-up action. The retrieval constraint and the cheap-path instruction are front-loaded with no filler.

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?

There is no output schema, so the description must explain returns — and it does, precisely (id, file, place, snippet). It also covers the search modality and the recommended next step, leaving nothing an agent needs in order to call this correctly.

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 coverage is 67%: query and limit are documented inline, while space_id is undocumented (though self-explanatory from the title and first sentence). The description contributes the important detail that query is matched both semantically and by keyword, which the schema's 'plain words' wording does not fully capture, but it adds nothing about limit or scoping behavior.

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?

The description names a specific verb and resource ('search all of a space's files'), enumerates the content types covered (readings, slides, transcripts, syllabus, assignments), and states the retrieval mode ('by meaning and keywords'). It also distinguishes itself from read_passage, so an agent can tell the two apart without inspecting schemas.

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?

It gives a clear operating rule: use this to locate passages, then 'open the ones you need with read_passage instead of reading whole files' — an explicit alternative plus the condition that selects it. It does not address when to prefer search_graph or how broad a query should be, but the core routing guidance is present.

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