Skip to main content
Glama

search_docs

Read-onlyIdempotent

Retrieve relevant runbook and postmortem passages plus live state of mentioned assets to answer operational questions and troubleshoot incidents.

Instructions

Search the runbooks and postmortems (GraphRAG): best passages plus the live state of the assets they mention.

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": {
      "question": "<question>"
    },
    "name": "search_docs"
  }
}

Input Schema

NameRequiredDescriptionDefault
kNo
questionYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.1/5.0
Behavior3/5

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

The annotations already declare the operation is read-only, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description usefully adds that retrieval is GraphRAG-based and that results combine best passages with live asset state. It does not disclose corpus breadth, freshness, pagination or result-count behavior, which limits it to adequate rather than rich.

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?

It is a single dense sentence with no filler, and the key scoping information (runbooks/postmortems, GraphRAG, what the result includes) is front-loaded. Every clause adds meaning.

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?

Because an output schema exists and annotations cover the safety profile, the description does not need to explain return values or side effects. It identifies the corpus and the composition of the result, which is useful for a two-parameter tool. However, it leaves the parameter semantics and the scope or freshness of the corpus unexplained, so it is only minimally complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

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 for the two parameters. It does not explain that "question" should be a natural-language query or that "k" controls how many passages are returned (default 3). The phrase "best passages" weakly implies ranked retrieval, but neither parameter's meaning or expected format is clarified.

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?

The description names a concrete verb ("Search") and concrete resources ("runbooks and postmortems") and states what comes back ("best passages plus the live state of the assets they mention"). That is enough for an agent to understand the tool without opening the schema. It does not explicitly contrast itself with siblings such as find_asset or root_cause_candidates, so it stops short of a 5.

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

Usage Guidelines2/5

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

There is no when-to-use or when-not-to-use guidance. The description does not say whether this should be preferred over impact_analysis, root_cause_candidates, or find_asset for particular questions, and it states no prerequisites or exclusions. Usage is only implied by the phrase "Search the runbooks and postmortems".

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