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

Goes well past the annotations: it discloses that no lease is required, that no CMS content is read, that the run is hermetic w.r.t. source+schema, and that failures surface as `ok: false` with diagnostics plus a separate `renderFailures` collection. That tells an agent exactly what a failed call looks like — the hardest thing to infer without 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?

Front-loaded with the action and scope, then failure semantics, then the hermeticity claim — a sensible ordering with no filler sentences. It runs as one dense block rather than being broken up, which slightly slows scanning but wastes no words.

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?

With no output schema, the description does the right work by sketching the failure return shape (`ok: false`, diagnostics, `renderFailures`). Annotations cover the safety profile. The only real hole is the undocumented required `websiteId`, which is the single thing an agent must supply.

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 carries the full burden for `websiteId`, yet it never mentions or scopes the parameter. The closing sentence about source and schema hints that evaluation is website-scoped, which is the only indirect signal, but an agent learns nothing about the identifier's meaning or format from the description.

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 — 'Runs the publish-time framework quality gate without changing source' — and enumerates the concrete checks (format, typecheck, lint, build, server-render). The phrase 'without changing source' and 'no lease is required' distinguish it from the adjacent head_publish/lease_acquire siblings.

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?

Usage is implied rather than stated: because it is framed as 'the publish-time framework quality gate,' an agent can infer it belongs before publishing, but the description never names head_publish as the alternative or gives an explicit when/when-not. There is also no guidance on when validating is unnecessary.

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