check_messages

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

With no annotations provided, the description carries the full burden and exceeds it: it discloses once-only delivery across three paths, that re-calling will not redeliver, that listing consumes nothing on the recipient's behalf, the blocking/timeout capping behavior, the [collab] mailbox = true requirement, and that plumb does not push. This is rich behavioral context far beyond what annotations would have supplied.

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?

The description is long but front-loaded with the core purpose, and nearly every sentence carries unique behavioral or routing information. The final 'Parameters:' line mildly duplicates the schema's wait_seconds description, a small redundancy, but the density of genuinely new information justifies the length.

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?

For a complex tool with no output schema and no annotations, the description covers an exceptional amount: delivery paths, once-semantics, threading via conversation_id, own-unread reporting with age, config requirement, and wait capping. The one gap is the exact return shape/fields, which the description only touches via conversation_id and age; with no output schema, that duty falls on the description.

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 100%, so the baseline is 3; the schema already fully defines wait_seconds including the cap. The description adds marginal strategic meaning beyond the schema — that a positive wait 'hands your turn to a peer instead of polling' and that the cap is 'kept below the client's own call timeout' — which an agent cannot infer from the bare parameter description.

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?

The description opens with a specific verb-plus-resource statement — 'Read messages other agents have sent you' — then scopes it precisely: 'Receive half of plumb's mailbox; leave_note is the send half.' It also discloses a second purpose (reporting your own unread mail), so an agent knows the full scope without opening any schema.

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?

It names the sibling alternative (leave_note as the send half) and points to the plumb-chat skill for full etiquette rules. It gives explicit when-to conditions for the wait behavior ('hand your turn to a peer instead of polling') and explains the immediate-return path ('Omit wait_seconds (or 0) to return immediately'). Nothing about selection is left to inference.

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