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

No annotations exist, so the description carries the burden; it discloses that replies include the shop's lines, total, deposit, message, and sender identity (shop vs. shop's assistant), which is genuinely helpful content-level context. It does not state that the call is read-only, whether replies are paginated, or what a pending/withdrawn request returns, leaving meaningful behavioral gaps for an unannotated tool.

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?

Three short sentences, front-loaded with the object of the call and followed by the polling directive. No filler; only mild terseness ('Your request') costs it a point.

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?

An output schema exists, so the description needn't enumerate return fields, and it wisely summarizes the content instead. Still missing for a polling tool: how to source request_id and whether polling should continue based on status — gaps that matter more than the return shape.

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 0% — request_id has no description in the schema — and the description never mentions the parameter, its UUID format, or where to obtain the id (presumably from homeowner_listRequests or homeowner_createRequest). "Your request" implies selection but provides no operational guidance for the one required input.

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 states what is returned — the request itself plus every reply so far — which distinguishes it from homeowner_listRequests (many) at a glance. However, the verb is smuggled in as "Poll this" rather than stated as "fetch a single request by id," so the naming of the operation is left implicit.

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?

"Poll this" is a genuine usage instruction that tells the agent to call it repeatedly, presumably after homeowner_sendRequest. But no alternatives are named (e.g., homeowner_listRequests for browsing, homeowner_pickReply for acting on a reply) and no stopping condition or when-not guidance is given.

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