Skip to main content
Glama

search_graph

Searches a persistent local knowledge graph built from past conversations to find related answers when exact keywords differ across sessions.

Instructions

Search the persistent local knowledge graph built from past conversations.

Use this for relationship-heavy questions where exact keywords may differ across sessions, such as "where did I solve a similar auth migration bug?". sources: "all" or any of claude, codex, gemini, opencode, cursor.

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": {
      "query": "<query>"
    },
    "name": "search_graph"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYes
sourcesNoall
max_resultsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.6/5.0
Behavior3/5

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

No annotations exist, so the description carries the full burden. It discloses useful context beyond the schema: the graph is local and persistent and built from past conversations, and results can span multiple sources. It does not address index freshness/staleness, whether results are ranked, or what a hit looks like beyond what the output schema provides.

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?

Three short blocks, front-loaded with purpose then usage then the source enumeration. No filler sentences, though the trailing 'sources:' fragment is tersely formatted compared to the prose above it.

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

Completeness3/5

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

A three-parameter read tool with an output schema reduces the burden, and the purpose and main use case come through. Still missing is any explanation of max_results and of index staleness or the need to refresh, which matters for a graph built incrementally from past conversations.

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 0%, so the description must compensate. It does add real meaning for 'sources' by enumerating allowed values (all, claude, codex, gemini, opencode, cursor), which the schema does not. However, 'query' gets no syntax or scope guidance and 'max_results' (default 5) is never mentioned.

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 plus a well-defined resource: 'Search the persistent local knowledge graph built from past conversations.' The phrase 'relationship-heavy questions where exact keywords may differ across sessions' clarifies it is a semantic/relationship retrieval rather than keyword lookup. It never names a sibling such as search_history, so differentiation is implied rather than explicit.

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?

Gives a clear usage condition ('relationship-heavy questions where exact keywords may differ across sessions') backed by a concrete example question. No when-not guidance and no named alternative are given, so the agent must infer that keyword-oriented lookups belong to another tool.

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