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

Annotations already declare readOnly, idempotent, closed-world, so the safety profile is covered. The description adds real semantic context beyond that: it explains what the `gated` value implies about candidate outcomes (automatic rejection vs invitation), which no annotation conveys. It does not discuss pagination or limits, but an aggregate count tool reasonably has none.

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 core question the tool answers, and the awkward line breaks are a formatting artifact rather than padding. Every sentence adds information: the metric, the gated semantics, and the sibling pointer. Slightly indirect phrasing keeps it from a 5.

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 need not enumerate return fields; it instead explains the one non-obvious flag (`gated`) that the schema cannot disambiguate. Combined with annotations covering safety and a single obvious parameter, an agent has everything needed to select and call it.

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?

There is a single required parameter, job_id, with 0% schema description coverage, so the description carries the burden of clarifying it. It refers to 'this job' and 'the employer's decision', which makes the scope of job_id inferable but never states the id format or whether it accepts slugs/names. Baseline adequacy, not compensation.

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 the resource (the review queue for a job) and what is reported: counts of candidates awaiting the employer's decision and those nearing expiry. It implicitly distinguishes itself from list_review_queue by noting that tool 'names them', so an agent can tell the aggregate from the enumeration. The only weakness is that the verb is phrased as a question rather than an explicit 'returns counts'.

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 alternative explicitly ('list_review_queue names them'), giving the agent a clear routing rule: use this tool for aggregate counts, the sibling for identities. It also supplies the decision rule for interpreting the result (gated true = auto-reject, false = invited). It stops short of stating explicit exclusions such as when a count is not needed at all.

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