Skip to main content
Glama

Search Library content

search_library_content
Read-onlyIdempotent

Browses or searches visible Library videos, articles, guides, and documents, including drafts. state matches the Library screen: draft, published, or cloning. It is not the internal video lifecycle and it is not the version status draft, publishing, or published. Guides appear when they already exist; this tool does not create them. Omit query to browse the Library. Render every result title as Title, never as bare text followed by a separate “Open” link. Search is discovery only: call inspect_library_content before relying on a result. A Library item must be published before it can be attached to a course. Omit cursor on the first request; reuse next_cursor with unchanged filters for more results. Search matches indexed titles, descriptions, narration, and guide step titles. Use focused topic keywords; if results are weak, try at most two relevant query variations and deduplicate by content ID. Inspect the strongest matches to verify relevance. Search is bounded to 500 indexed candidates and may change during pagination; never claim an exhaustive Library audit.

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_library_content"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNoDefaults to relevance for text search and created_desc when browsing. Creation date is not a freshness or verification date.
queryNoOptional. Omit to browse all visible Library content, including drafts.
cursorNoOmit initially. To continue, copy the previous response next_cursor.
statusNoOptional Library screen status filter: draft, published, or cloning.
page_sizeNoMaximum matching items in this response, not a page number.
content_typesNoDefaults to video, article, guide, and document.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive, but the description adds substantial behavior beyond them: search covers indexed titles, descriptions, narration, and guide step titles; it is bounded to 500 indexed candidates; the index may change during pagination and results are never exhaustive. That last disclosure directly prevents an agent from misreporting a complete audit.

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?

The definition is front-loaded with purpose and scoping before tactics, and nearly every sentence carries an actionable constraint. It drifts slightly toward redundancy with the inspect-before-relying guidance stated twice and a presentation-format instruction ("Render every result title as [Title](open_url)") that sits oddly among search semantics.

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?

With no output schema, the description carries the full disclosure burden and covers result fields implicitly (content IDs for deduplication, open_url for linking), pagination limits, result volatility, and the discovery-vs-verification split. Nothing an agent needs to call this correctly or interpret results safely is missing.

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 contributes real meaning the schema lacks, notably that `state`/status maps to the Library screen and is NOT the internal video lifecycle or version status — a distinction the enum alone cannot convey. `cursor`, browse-by-omitting-`query`, and result-matching scope are also reinforced in operational terms.

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?

Opens with a specific verb+resource pair ("Browses or searches visible Library videos, articles, guides, and documents, including drafts") and immediately scopes what it is not: guide creation and internal video/version lifecycle states. An agent can distinguish it from inspect_library_content, import_library_content, and publish_library_content without opening any schema.

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?

Explicit when-to-use rules are supplied throughout: omit query to browse, omit cursor on the first request, reuse next_cursor with unchanged filters, call inspect_library_content before relying on a result, and use at most two query variations if results are weak. It also states a prerequisite rule (an item must be published before attaching to a course) that steers the agent to a different tool for that goal.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources