Skip to main content
Glama

search_evidence

Search recorded engineering evidence across cases to retrieve raw material and prior session logs for review—not past conclusions or decisions.

Instructions

Search this engineer's recorded evidence across all their cases — the raw material, never past conclusions. When there is room left, results also include material from BEFORE casebook was installed (kind="pre_install"): the engineer's own words imported from old session logs, with the source session. Treat those as raw material only — they are not decisions or constraints, and they may describe approaches that were later abandoned. A hit is retrieval, not a conclusion.

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_evidence"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
queryYes
include_archivedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose non-obvious behavior: pre-install material appears only 'when there is room left', arrives with its source session, and may describe abandoned approaches. Gaps remain — nothing about result ordering, excerpt size, or whether hits are ranked or excerpted — but the semantic caveats are unusually well surfaced.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The scope limitation is front-loaded and the pre_install caveat is well placed, but the 'raw material, not conclusions' idea is asserted three times across the text ('never past conclusions', 'Treat those as raw material only', 'A hit is retrieval, not a conclusion'). Deliberate emphasis, yet it costs a sentence of budget that parameter documentation needed.

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?

Without annotations or an output schema and with 0% parameter coverage, the description should ideally cover both invocation semantics and expected result shape. It handles the interpretive risk of pre-install and abandoned-approach material thoroughly, but an agent still cannot tell what a hit looks like or how include_archived changes results.

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 three bare parameters, and it largely does not. 'When there is room left' gestures at limit, but query syntax and especially include_archived — a meaningful choice given the tool searches an engineer's case history — are never explained anywhere.

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 uses a specific verb and resource ('Search this engineer's recorded evidence across all their cases') and draws a sharp line against concluded knowledge ('never past conclusions'), which implicitly separates it from conclusion-oriented siblings like search_prior. It stops short of naming any sibling, so the differentiation is inferential 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 Guidelines3/5

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

The contrast with 'past conclusions' implies the retrieval-only use case, but there is no explicit statement of when to choose this over search_prior, find, or overview, and no prerequisites. Guidance is present but must be inferred from the framing rather than stated as a rule.

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