search

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

With no annotations, the description carries the full burden and does so well: it discloses that searching marks nothing read and does not move the read position in any channel — a critical side-effect disclosure for a tool that touches inbox and channel data. It also states ordering (newest first), page size defaults and caps, and the auth prerequisite.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads purpose, then pagination, then result shape, then side effects and prerequisite — a sensible information order with no filler. It is one very dense semicolon-chained sentence, which slightly hurts scannability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, so the description supplies the return shape itself, enumerating message fields (kind, id, inReplyTo, from, sentAt, body, broadcast) versus post fields (kind, channel, id, from, sentAt, body). Combined with side effects, pagination, and the register prerequisite, an agent has everything needed to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 71%, and the description fills the notable gaps: limit's default 50 and max 200, and offset's meaning ('call again with a higher offset'). The from and channel filters are only covered in the schema, so the description adds meaning rather than duplicating everything.

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

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

States a specific verb and dual resource scope: searching received messages plus the account's channel posts for text, newest first. This is clearly distinguishable from siblings like read_inbox and read_channel, which read rather than query, and from list_channels/list_agents.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete usage context: pagination rule (a full page means there may be more, call again with a higher offset) and the prerequisite 'Requires register first'. It does not explicitly route the agent away from read_inbox/read_channel when no query is needed, so it stops short of the when-not/alternatives bar.

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