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

The description discloses write behaviour (write-safe on dev, read-only on live), costs (2-4 min compute), and asynchronous nature (returns run_id, poll status). This goes well beyond the simple destructiveHint annotation, giving full transparency.

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 a single dense paragraph with many semicolon-separated clauses, but each clause carries unique, necessary information. It is not overly verbose for the amount of caveats covered, though a more structured layout would improve readability.

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?

It covers all essential context: prerequisites, safety guarantees, operational costs, async handling, and how to poll results. The description is fully self-contained for an agent deciding to call this 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?

All parameters have schema descriptions (100% coverage), so the baseline applies. The description text does not add extra parameter semantics beyond the schema, so it remains at the baseline level.

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 clearly states the tool runs the full behavioural test suite against a published bundle in the project's own deployed app, and distinguishes it from the smoke test. This gives a precise, actionable purpose.

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 explicitly states when to use it (after build_validate and build_doctor pass, on a deployed and seeded project), when not to (not a per-edit check), and contrasts with the lighter smoke test. This provides clear guidance on selection.

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