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

Adds context beyond the annotations (destructive/openWorld/non-idempotent) by disclosing the quote-approval prerequisite, the returned build_run_id, the polling pattern via get_build wait:25, and the completion condition artifact_ready. This is exactly the operationally necessary context for a mutating build step.

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: purpose, follow-up polling contract, and safety constraint. No filler, and the most important information (what it builds and what it returns) is front-loaded.

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, yet the description supplies the return value (build_run_id) and the completion signal (artifact_ready) that an agent needs to proceed. Combined with the destructive annotation and the pub/share exclusion, nothing essential is missing for a 3-param build tool.

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?

At 67% schema coverage, concept_id and direction are already documented in the schema, but audit_id has no description in either place, and the tool description adds no parameter guidance at all. Baseline 3 is appropriate since the schema carries most of the load.

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+resource: 'Build the design the user selected into a complete HTML page.' It also names the precondition (approval of the live quote) and the return value (build_run_id), which distinguishes it from siblings like generate_concepts or publish_page.

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?

Explicit when-to-use (after quote approval), explicit routing to the follow-up tool (get_build with wait:25), and an explicit exclusion ('Do not publish or share the page without the user asking') that separates it from publish_page/share_page.

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