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

Annotations already declare this is a non-read-only, non-idempotent, open-world mutation, so the safety profile is partly covered. The description adds real behavioral context beyond them: a gating precondition (quote approval), the async return value (build_run_id), and the completion signal (artifact_ready) needed to know when the build is done.

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?

Three tight sentences, front-loaded with the core action, followed by the polling contract and the constraint. Every sentence carries an actionable instruction with no filler.

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, and the description compensates by naming the returned build_run_id and the artifact_ready completion condition, plus the quote-review prerequisite. Minor gaps remain (error/failure behavior if approval is missing), but an agent has enough to call and poll correctly.

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 coverage is 67%; concept_id and direction are documented inline ('From get_concepts', 'Optional plain-English steer'), while audit_id is undocumented in both places. The description only alludes to the concept via 'the design the user selected' and adds no syntax or format detail, so baseline 3 is appropriate.

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 ('Build the design ... into a complete HTML page') and clarifies scope by noting it must follow quote approval. It is clearly distinguishable from siblings publish_page and share_page, which it explicitly tells the agent not to invoke unprompted.

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 a clear precondition (live quote must be approved) and an exclusion ('Do not publish or share the page without the user asking'), which routes the agent away from publish_page/share_page. It also prescribes the follow-up polling step (get_build with wait:25). It stops short of naming the alternative tools outright.

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