Skip to main content
Glama

find

Search past Worktrail threads for decisions, constraints, ruled-out options, notes, and next steps; returns matching refs and thread context when an engineer cites earlier work.

Instructions

Pull past context across every thread when you need it: decisions, constraints, ruled-outs, focus/open/next declarations, notes and close results whose text contains every word of query — one line each with its number (ref) and thread, in-force before superseded, newest first; evidence hits fill the remaining room. Use it when the engineer refers to something from before ('the one we rejected', 'why did we…') or you need a record's number. Notes are marked interpretation, not evidence. Then trail(case_id) or inspect(ref).

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": "find"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
queryYes
include_closedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

No annotations, so the description carries the full burden and discharges much of it: matching is 'every word of query', results are one line each with ref and thread, ranked 'in-force before superseded, newest first', with 'evidence hits fill the remaining room' and notes flagged as interpretation not evidence. It omits return limits, pagination, and any read-only/safety statement, but the core behavior is well disclosed.

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?

Purpose is front-loaded, then usage, then follow-ups, with no filler sentences. The middle clause is dense with dashes and semicolons packing many record types, which costs a little scannability but every clause carries real information.

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?

For a three-parameter retrieval tool with no output schema, the description conveys output shape (one line each with ref and thread) but leaves limit and include_closed undefined and doesn't fully explain how evidence and records are interleaved in results. Adequate but with visible gaps.

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 coverage is 0%, so the description must compensate. It defines query semantics precisely ('whose text contains every word of query'), but limit and include_closed are never explained in either the description or the schema; 'remaining room' only hints at limit. Partial compensation justifies a middle score.

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?

A concrete verb ('Pull past context') with an explicit scope ('across every thread') and an enumerated set of resources: decisions, constraints, ruled-outs, declarations, notes, close results. It distinguishes the tool from trail(case_id) and inspect(ref) as follow-ups, but doesn't explicitly separate its behavior from the sibling search_prior and search_evidence, which an agent might reach for first.

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 trigger with concrete example phrasings ('the one we rejected', 'why did we…') and a second condition ('you need a record's number'). It also names the downstream actions ('Then trail(case_id) or inspect(ref)'). It stops short of stating when NOT to use it versus search_prior/search_evidence, but the context is strong.

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