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

With no annotations, the description carries the full burden and does real work: one call holds at most 45 s regardless of timeout_s, larger values are silently clamped rather than rejected, the MCP client aborts longer calls (#988), and the response contains timed_out:true. It omits whether the operation is read-only and what a successful (non-timeout) return looks like.

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?

It is compact and front-loads the core claim (bounded, client-neutral, resumable) before the caveats. The densely parenthesized clauses and bare issue references (#988, #1025) add noise for little agent benefit.

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 stateless wait tool with no output schema, the description covers the timeout ceiling and the timed_out flag, which is the critical failure mode. It leaves unclear what is returned when the review actually completes, how to interpret review_id, and how poll_after_s relates to the described background-timer behavior.

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 description coverage is 0%, so the description must compensate for three parameters. It adds genuinely useful semantics for timeout_s (effective 45 s cap, clamping rather than rejection), but review_id and poll_after_s are never explained, and the mention of monitor.interval_s references a field not in this schema, which muddies rather than clarifies poll_after_s.

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?

"Bounded, client-neutral wait" names the operation and its defining constraint (bounded, stateless-safe), and the title supplies the resource (review completion). It is clearly distinct from siblings like submit_review or get_findings, though the description itself never states that the wait is on a review identified by review_id.

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 gives an explicit when-not-to-use: do not call this in a loop, because a background timer on status_url keeps the poll cadence (#1025). That is a substantive usage rule. It stops short of routing to siblings (e.g. when to prefer polling get_findings directly versus waiting here).

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