Skip to main content
Glama

Search backed-up chats

search_chats
Read-onlyIdempotent

Search the user's backed-up ChatGPT and Claude chats from the last 10 days to recall what they said in another conversation, returning matching chats with the lines that matched.

Instructions

Search the chats the user backed up to Thread with Thread's own browser extension (their last 10 days of ChatGPT and Claude chats, stored in their Thread account). For when they ask about something they said in another chat. Returns matching chats with the lines that matched.

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_chats"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
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 the safety profile is covered. The description adds genuinely non-obvious behavior: the data only exists if the user installed Thread's browser extension, is capped at 10 days, covers only ChatGPT and Claude, and returns matched lines rather than whole chats. It doesn't mention result limits or pagination, but with an output schema present that is a smaller gap.

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 sentences, front-loaded with the resource and scope, then the usage trigger, then the return shape. The parenthetical about 'Thread's own browser extension' earns its place by explaining data provenance, though the phrasing 'the chats the user backed up' is slightly redundant with the parenthetical that follows.

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 one-parameter read tool with annotations and an output schema, the description covers provenance, time window, source platforms, trigger condition and return shape. The main remaining gap is routing: with siblings like search_memory, read_chat and canvas_search available, one clause on when this is not the right tool would close the loop.

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 0% and the single parameter is documented only as a bare string titled 'Query', so the description carries the burden. It implies a natural-language question ('something they said in another chat') but never states whether matching is semantic or keyword-based, nor how multiple words combine. That is useful implication but not enough to fully compensate.

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 gives a specific verb (Search) and a precisely scoped resource: chats backed up to Thread via its browser extension, limited to the last 10 days of ChatGPT and Claude chats. It stops short of explicitly distinguishing itself from near-neighbors like read_chat or search_memory, so an agent must infer that difference from the word 'Search' alone.

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?

'For when they ask about something they said in another chat' is a clear, concrete trigger condition that an agent can pattern-match against a user request. There are no explicit exclusions or named alternatives, so the agent gets a positive signal but no guidance on when a different search tool should win.

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