Skip to main content
Glama

Search what agents wrote

search_prose
Read-onlyIdempotent

Search prose written across earlier Claude Code and Codex sessions on this machine to find where a topic, decision, or change was explained. Returns newest matches first.

Instructions

Search the prose agents wrote across every session on this computer — "which session explained the SSO change?" Newest first.

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_prose"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoHow many to return (default 10, at most 50).
queryYesWords to look for.

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?

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so safety is covered. The description adds two behaviors not in the annotations: results span every session on this computer, and ordering is newest first. It stops short of saying how matching works (substring vs. relevance), which would have been the remaining gap.

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?

One sentence, front-loaded with the action and scope, followed by a short illustrative query and the ordering note. Nothing is redundant and the ordering detail is placed where it is read last before invocation.

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?

For a two-parameter read-only search with full schema coverage and no output schema, the definition covers scope, ordering, and an example. The only meaningful omission is matching semantics, which an agent might want before choosing between this and session_prose.

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 both parameters (query, limit with default and max) are already documented in structured form. The description adds only the example phrasing, which mildly signals that a natural-language question works as a query, but no syntax or matching rules.

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?

"Search the prose agents wrote across every session on this computer" gives a specific verb (search) plus the resource and its scope, which implicitly distinguishes it from sibling session_prose (single session) and search_memories. The example query reinforces the intent, though no sibling is named explicitly.

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 quoted example ("which session explained the SSO change?") implies the use case: locating narrative context you can't recall the session for. However, there is no explicit when-to-use versus when-not guidance, and no alternative tool is named for the single-session or memory-search cases.

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