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

Annotations already cover the read-only, non-destructive profile, yet the description adds substantive behavior: percentage is work progress not an ETA, collected Answers may await analysis, a failed/cancelled Scan can show 100% so status/outcome determine success, and the call never starts or repairs a Scan. This is exactly the extra context the annotations cannot convey.

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?

Dense but front-loaded: identity and scope first, then return semantics, then polling rules, then the negative boundary and the sibling pointer. Every sentence earns its place, though the polling guidance makes it longer than strictly minimal.

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 return values need not be enumerated, and the description still adds the interpretive caveats (percentage vs completion, failed-at-100%) that the output schema alone would not resolve. Nothing needed to call this correctly is missing.

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 100%, so the baseline is 3, but the description adds real meaning beyond the schema: omitting scanId yields the five most recent Scans, and siteId may be a Site or Topic (with topics supporting manual baseline scans).

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 resource plus scope: 'Read one Scan by ID, or the five most recent Scans when scanId is omitted, for a Site or Topic.' An agent can distinguish this from list_scans and trigger_scan without opening a 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 explicit operating conditions: pin scanId to follow one scan, poll 15–30 seconds apart, respect retryAfterSeconds on rate-limit errors, stop on completed/failed, and use list_scans for paginated history. When/when-not and the alternative are both named.

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