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

Annotations already cover read-only, idempotent, non-destructive, closed-world. The description adds extensive behavior: lastScanAt semantics (one-page re-checks don't move it), scan.phase enum values and meaning, first-scan findings state, unverified-site scanning policy, verifyUrl, and addSiteUrl on empty account. This is substantial disclosure beyond structured fields.

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?

Front-loads purpose, then packs return-field semantics into a dense paragraph. Given no output schema, most sentences earn their place, but it could be better structured with bullets. Appropriate length for the information density.

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?

No output schema exists, so the description must carry return values. It details fields, scan phases, verification consequences, and empty-account response, making the tool callable and interpretable without extra docs. Minor omission: no pagination or ordering info, but list semantics are otherwise covered.

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?

Zero input parameters and an empty schema. The rule baseline for 0 params is 4, and no parameter descriptions are needed.

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 a specific verb and resource ('List the sites this account can see') and immediately scopes it to the account's visible sites. It makes the tool's role clear against add_site/verify/rescan_site siblings, though it does not explicitly name an alternative tool.

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?

No when-to-use guidance, no when-not, and no alternatives are mentioned. The description is entirely about output fields and behavior, leaving the agent to infer that this is the discovery tool.

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