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

Annotations already declare this a safe, idempotent, non-destructive read. The description adds behavior the annotations cannot convey: the call blocks, times out after a default of 25s (max 30s), and signals expiry via 'timedOut: true' rather than an error. It does not discuss what happens to requests that arrive between calls beyond the 'after' cursor, but the latency and timeout semantics are the critical missing pieces and they are covered.

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 tight sentences with the blocking behavior front-loaded, then the cursor parameter, then the timeout/retry contract. No filler, and each sentence carries information an agent needs to drive the polling loop.

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?

There is no output schema, so the description carries the return contract; it names the two things that matter (the new requests and 'timedOut: true') but does not sketch the shape of a returned request object. For a four-parameter long-poll tool with full annotation coverage, that is a small remaining gap rather than a blocking one.

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 baseline is 3. The description still adds real meaning: it explains 'after' as 'the last request ID you have seen' (schema only says 'requests captured after it'), and supplies the default timeout of 25 seconds, which the schema's '1 to 30 seconds' description omits.

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 blocking behavior ('Block until a webhook inbox receives a request') plus the resource returned ('the new requests'). The webhook-inbox scope distinguishes it from the other wait_for_* siblings (wait_for_email, wait_for_sms, wait_for_event) and from inspect_webhook_inbox without needing to open 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?

Gives concrete usage guidance: pass 'after' with the last seen request ID to avoid re-reading old requests, and call again after a timeout to continue waiting — effectively describing the long-poll loop. It does not name an alternative for non-blocking checks (e.g. inspect_webhook_inbox), so it falls short of explicit when-not guidance.

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