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

The description clearly discloses the non-obvious behavior: it queues a card rather than publishing, the human taps 'Publish page' to merge the frozen PR, and calls are refused for companies without a site config. It also adds the approval workflow ('write-tier — first use may require a manager's approval') and instructs not to re-ask. The destructiveHint annotation is contextualized, not contradicted: the tool enables a human-initiated publish rather than performing it directly.

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?

The description is front-loaded with the core purpose and then organized into a caveat, a routing sequence, and an approval note. It is longer than the shortest possible definition, but the extra sentences are earned: they explain the human-in-the-loop behavior, the refusal condition, and the approval/re-ask policy. Only minor redundancy appears between the opening condition and the Routing paragraph.

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?

For a tool with no output schema, this description is complete: it specifies when to call, what must happen first, which values to send, how the human confirmation works, what causes refusal, and how approvals behave. An agent has everything needed to invoke publish_site correctly without further clarification.

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 input schema already documents every parameter and its role. The description reinforces which four parameters to pass ('screenshot_artifact_id, preview_url, pr_number, and head_sha') and ties them to the browse_url/PR workflow, but it does not add substantive meaning beyond the schema for optional fields like slug and companyId.

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 opens with a specific verb and resource: it 'Tee[s] up a ONE-CLICK publish card for THIS company's marketing site (Learn / SEO pages).' It goes further and disambiguates from direct-publish siblings by stating 'It NEVER publishes: it queues a Command Center card' and 'this tool never publishes another company's site,' making the tool's role unmistakable.

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 gives an explicit precondition and sequence: 'Call after you opened a PR and took a browse_url screenshot of the preview' and 'browse_url the preview first, then call publish_site with its screenshot_artifact_id, preview_url, pr_number, and head_sha.' It also names the alternative behavior to avoid ('Use instead of asking anyone to open Lovable or GitHub') and states a refusal condition when no site config exists.

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