Skip to main content
Glama

Search a mailbox

search_conversations

Finds the threads of one mailbox by their subject, their text, the people on them or the names of the files they carried, best answer first. Call list_sender_addresses to find the box. This is how you look a mail up when you know a word of it and not where it is.

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": {
      "box": "<box>",
      "q": "<q>"
    },
    "name": "search_conversations"
  }
}

Input Schema

NameRequiredDescriptionDefault
qYesWhat is being looked for. Plain words are all required, "a phrase in quotes" is looked for as written, "or" offers an alternative and a leading "-" excludes a word.
boxYesThe address of the mailbox to look in, for example "simon@sonentreprise.com": call list_sender_addresses to find it. One of its aliases names the same mailbox. A support queue is not a mailbox and has no folders.
limitNoHow many threads to bring back, 1 to 200. Defaults to 100.
folderNoNarrows to one folder of the box: one of inbox, sent, drafts, spam, trash, archive, or the id of a folder a person made (list_folders gives them). Left out, the whole box is searched, which is usually what is wanted: a mail is looked for precisely because nobody remembers where it was filed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / box / description
      Previous value: -"The address of the mailbox to look in, for example \"simon@sonentreprise.com\": call list_sender_addresses to find it. A support queue is not a mailbox and has no folders."New value: +"The address of the mailbox to look in, for example \"simon@sonentreprise.com\": call list_sender_addresses to find it. One of its aliases names the same mailbox. A support queue is not a mailbox and has no folders."
  2. First observed

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description carries the full disclosure burden. It does add useful behavior: results are relevance-ranked ("best answer first") and the whole box is searched when folder is omitted. It says nothing about permissions, pagination or result shape, which matters for a search tool that can match at most the returned limit.

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 what is searched and what gets matched. The closing sentence is slightly conversational in tone but still conveys the use case rather than padding.

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 four-parameter search with no output schema and no annotations, the definition covers the matching scope, ranking, default all-folders behavior and how to obtain a valid box. The main remaining gap is what a returned thread looks like and how to fetch more than the limit.

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 100% and the schema itself documents the query syntax, box address, limit range and folder values in detail. The description adds no parameter-level meaning beyond that, so the baseline 3 applies.

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?

States a specific verb and resource ("Finds the threads of one mailbox") and enumerates what can be matched: subject, text, participants, attachment filenames. It stops short of naming the sibling it contrasts with (list_conversations), so the browse-vs-search split is only implied.

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?

"This is how you look a mail up when you know a word of it and not where it is" gives a clear, concrete selection condition, and the description also routes the agent to list_sender_addresses to resolve the box. There is no explicit when-not statement or named alternative for browsing a folder.

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