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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. On top of that the description discloses genuinely non-obvious semantics: n_resources counts resources ever seen while current_verdict_mix and n_payable_last_full count only the latest full scan, and verdict_since can span unmeasured weeks because a scan missing the resource does not break the run. That is real behavioral context an agent cannot derive from annotations.

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?

With no output schema, the field-by-field explanation is load-bearing rather than padding, and it is front-loaded with the purpose and field inventory before the caveats. A few clauses restate the same latest-full-scan distinction (n_resources vs current_verdict_mix/n_payable_last_full), which costs some tightness, but overall every sentence earns its place.

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?

Because there is no output schema, the description carries the full burden of explaining returned fields and does so thoroughly, including the subtle veracity caveat about verdict_since. The one real hole is the undocumented 'host' argument, which leaves an agent guessing at input format. For an otherwise complex read-only summarizer, it is close to complete.

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 one required parameter, 'host', and schema description coverage is 0%. The description never says what form the host argument takes (hostname, identifier, URL fragment) or how to obtain it, so the single parameter is undocumented in both the schema and the prose. With one parameter and no coverage, the description should have compensated and does not.

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 first clause states a specific verb and resource ('Summary for a host') and explicitly bounds scope with '(no time series)', which is a meaningful disambiguation from time-series siblings. It immediately enumerates the returned fields, so an agent knows exactly what it gets. It does not name a sibling tool to contrast against, but the sibling set (drift_status, payability_verdict, etc.) does not obviously overlap, so this is a minor gap.

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?

Nothing states when to call this versus alternatives like payability_verdict or catalogue_stats, nor any prerequisites such as whether a scan must exist first. The guidance about interpreting last_checked_at vs verdict_since is about reading results, not about choosing the tool. Usage is only implied by the tool's name and scope.

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