Skip to main content
Glama
inbox-recall

inbox-recall

by joey12725

Search messages

search_messages
Read-only

Search synced chat networks with hybrid semantic, keyword, and fuzzy queries; return ranked excerpts with context and citable message IDs, and filter by sender, chat, network, direction, and time.

Instructions

Hybrid semantic + keyword + fuzzy search across every synced chat and network. Returns ranked matches as conversation excerpts with surrounding messages, each line tagged with a citable message id. Filter by sender, person, chat, network, direction and time (when accepts plain English such as 'last spring' or 'march 2024'). Leave query empty to list messages matching the filters, newest first. Paginate with next_cursor.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_messages"
  }
}

Input Schema

NameRequiredDescriptionDefault
chatNoChat title fragment or numeric conversation id.
modeNohybrid
whenNoTime range in plain English, e.g. 'last summer'.
afterNoISO date or datetime (inclusive).
limitNo
queryNoWhat to look for: a topic, phrase or question.
beforeNoISO date or datetime (exclusive).
cursorNonext_cursor from a previous call with the same query.
formatNotext: compact, citation-tagged transcript (default). json: the full structured result.text
personNoOnly conversations that include this person.
senderNoWho wrote the message (name or handle). 'me' = the user.
contextNoMessages of context before and after each match.
networkNoe.g. whatsapp, signal, instagram, imessage, telegram.
directionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations only declare read-only and closed-world, so the description carries the real burden and does so well: it discloses ranked recall, excerpt-shaped results with surrounding context, citable message ids, and cursor pagination semantics. It's not exhaustive on cost/limits of 'search across every synced network', but it substantially exceeds what the annotations tell the agent.

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?

Six tight sentences, front-loaded with purpose, then results, then filtering, then the empty-query mode, then pagination. Nothing is padding and the ordering matches how an agent would need the information.

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 14-parameter, no-required-parameter tool with no output schema, the description covers return shape, citation format, and pagination — the things the schema cannot convey. A few parameters (mode, context depth, limit) are only covered by the schema, which is acceptable at 79% coverage but leaves a small gap.

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 already 79%, so the schema does most of the work on filters, enums and bounds. The description adds genuine meaning only for the empty-query case and reinforces plain-English `when` handling; it never explains `mode`, `context`, `limit`, or `after`/`before` interplay, so it sits at the baseline rather than above it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource ('Hybrid semantic + keyword + fuzzy search across every synced chat and network') and states the retrieval model and scope. An agent can distinguish this from get_messages or get_conversation purely from the text, since this is a ranked search rather than an id-based fetch.

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?

It gives usable context: search when you have a topic/phrase/question, and 'Leave query empty to list messages matching the filters, newest first' defines an explicit degenerate mode. It stops short of naming when to prefer a sibling (e.g., get_conversation for a full thread) or any exclusions, so it lands at clear-context-but-no-alternatives.

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