ai-agent-channel

list_messages

Read-only

Search message history with filters on topic, text, status, kind, work status, or pin_key, and project fields to return headers only. Get newest first, then fetch full records as needed.

Instructions

Search the full message history with optional filters. Use 'topic' for substring match on the topic, 'text' for substring match across topic OR body (a field name, an identifier, a phrase); both filters are at most 200 characters. 'status' (open/resolved), 'kind' and 'work_status' for exact match on structured fields. Returns newest first. 'pin_key' filters to proposals STRUCTURALLY linked to a pin (the field set at send time) — messages that merely mention the key in their text are deliberately NOT matched, which is the difference between this and text=. Optional 'fields' projects the response: a list of field names, or the single value 'headers' for the usual listing set (everything except the bodies). Omit it and the full record comes back. Use it when a listing over a long history would otherwise be too large to return — bodies dominate the size, and a 'which messages' question rarely needs them; fetch the ones you want individually afterwards.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`kind`	No
`text`	No
`limit`	No
`since`	No
`topic`	No
`fields`	No
`status`	No
`pin_key`	No
`to_role`	No
`from_role`	No
`unread_only`	No
`work_status`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 12, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations only declare readOnlyHint=true. The description adds real behavioral context beyond that: results return newest first, pin_key matches only structurally linked proposals (not text mentions), and the fields projection omits bodies. No contradiction with annotations. The safety profile is covered by the readOnly annotation, so the description's added sorting/linking semantics justify a strong score.

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?

The description is a single dense paragraph but front-loads the core purpose before detailing filter semantics. Every sentence earns its place; the pin_key and fields explanations, while lengthy, clarify genuinely subtle behavior. It could be broken into bullet points for scannability, but nothing is wasted.

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?

For a 12-parameter tool with 0% schema coverage, the description covers the highest-risk semantics (pin_key linking, fields projection, substring vs exact match) but leaves limit, since, to_role, from_role, and unread_only undocumented in both schema and description. The presence of an output schema covers return format. Given the tool's complexity, the gaps on five parameters prevent a higher score.

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 0% with 12 parameters, so the description carries the full burden. It explains the nuanced semantics of the tricky params well: topic (substring on topic), text (substring across topic OR body), status (open/resolved), kind/work_status (exact match), pin_key (structural link), and fields (projection list or 'headers'). However, it omits five parameters entirely — limit, since, to_role, from_role, and unread_only — leaving their meaning to the bare schema names.

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+resource: 'Search the full message history with optional filters.' It clearly states scope (full history), the operation (search), and what the filters do. It also distinguishes pin_key from text matching, which helps separate this tool's unique behavior. The purpose is unambiguous.

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?

Provides actionable usage context: when to use the 'fields' projection ('Use it when a listing over a long history would otherwise be too large'), and clarifies the pin_key vs text= distinction. However, it does not explicitly route the agent away from sibling tools like search_messages, message_history, or read_inbox, leaving some selection inference to the agent.

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