Skip to main content
Glama

search_runs

Full-text search across previous runs' hop logs (inputs and outputs) on graphs the caller owns — the same recall the in-run search_runs tool gives agents. Returns content-ranked hits plus laneHits (recent hops of graphs whose name matches the query), with run/node/hop provenance. Pass days to bound to recent runs.

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_runs"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNoOptional: only events finished within the last N days — for 'recent X' recall
limitNoMax results per set, default 5, up to 10
queryYesWords to search for — plain full-text query
graphIdNoOptional: restrict to one graph

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / days
      Added value: +{
      +  "description": "Optional: only events finished within the last N days — for 'recent X' recall",
      +  "type": "number"
      +}
    • changedInput schema / properties / limit / description
      Previous value: -"Max results, default 5, up to 10"New value: +"Max results per set, default 5, up to 10"
  2. First observed

TDQS

A3.9/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the burden. It does add real value: an access boundary ('graphs the caller owns'), a two-part return shape (content-ranked hits plus laneHits), and provenance fields (run/node/hop). It still omits pagination behavior, whether reads are side-effect free, and any limits/cost beyond the schema's numeric cap.

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 tightly packed sentences, front-loaded with the core action and scope, then return shape, then the recency hint. Minor redundancy with the schema on days and slightly dense inline parentheticals keep it from a 5.

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 and no annotations, the description does what it must: names the resource universe, sketches the return payload and ordering (content-ranked, laneHits, provenance), and flags the ownership restriction. Missing only edge-case behavior such as empty-result handling and pagination across the 'sets'.

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%, so the schema already explains query, days, limit, and graphId. The description mostly restates days ('bound to recent runs') without adding format, syntax, or matching semantics (e.g., stemming, phrase support) beyond what the schema provides.

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?

States a specific verb and resource — 'full-text search across previous runs' hop logs (inputs and outputs)' — plus a scope qualifier ('on graphs the caller owns'). This is clearly distinguishable from siblings like get_run (fetch one run by id) or list_graphs (enumerate graphs).

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 clear triggering context: use it to recall past run content by free text, and 'Pass days to bound to recent runs' for recency-style queries. It does not name an alternative or state when NOT to use it (e.g., 'use get_run when you already have a run id'), so it falls short of full routing guidance.

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