Skip to main content
Glama

Search the knowledge graph

search_graph
Read-onlyIdempotent

Search a space's knowledge graph to find learned facts and the reasoning chains linking them. Returns recent facts when no query is given.

Instructions

Search one space's knowledge graph (each space has its own): the facts (propositions) the learner has learned and the reasoning chains connecting them. Without a query, returns the most recent facts.

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_graph"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMost facts to return (default 30).
queryNoWhat to look for, in plain words (matched by meaning and by keywords).
space_idNoThe space id from list_spaces, or "none" for lessons without a space (the default).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.1

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, closed-world and non-destructive, so the safety profile is covered. Beyond that, the description adds meaningful behavior: results are scoped to one space (each space has a separate graph), the content of a result is both facts and the chains connecting them, and the no-query default is recency ordering. Pagination and result ordering when a query is present remain unstated.

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 short sentences, front-loaded with the purpose and scope, with the fallback behavior trailing where it belongs. No filler wording earns no credit, and nothing is buried.

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?

With no output schema, the description carries the burden of describing results and does so at a high level (facts plus reasoning chains). For a 3-optional-parameter read tool whose annotations are complete, this is nearly sufficient; only the shape of the returned chains and ordering under a query are left undefined.

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%, with limit, query and space_id all documented in the schema itself, so the baseline is 3. The description reinforces the space scoping and the meaning/keyword matching, but adds no format or syntax detail beyond what the schema already provides.

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 (search) and resource (a single space's knowledge graph), and clarifies what the graph contains: learned propositions plus the reasoning chains linking them. The per-space scoping in the parenthetical is a useful disambiguator, but it never explicitly distinguishes itself from the sibling search_space_files, so the agent must infer the graph-vs-files boundary.

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?

"Without a query, returns the most recent facts" gives real guidance on when to call it query-less (browse mode), which is more than most definitions offer. However, it never names an alternative tool or states when to prefer file search or lesson reading over graph search, leaving tool selection to inference.

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