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

Annotations declare destructiveHint=true and openWorldHint=true, but the description adds substantial context beyond them: throwaway accounts are created and deleted, Stripe runs in TEST mode only (otherwise refused), no real email is sent, and the run is rate-limited at ~1-3 min. These are exactly the side-effect details that determine whether an agent should invoke a destructive, open-world tool.

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 scope, then exclusions and timing, then the flow, which is good ordering with no filler sentences. The long semicolon-separated checklist of tested areas is dense and slightly hard to scan as a single paragraph, keeping it off a 5.

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?

There is no output schema, and the description compensates by describing the return: a score plus pass/fail/skip per check with evidence and the exact fix. Combined with timing, dry-run behavior, and the post-run consumer (build_go_live reports the latest result), an agent has everything needed to call and interpret it.

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 100%, so the schema already documents all four parameters; the description reinforces the key constraint that target is always 'preview' and restates what dry_run does. It doesn't add detail for budget_s beyond the schema, so it sits just above the baseline rather than redefining parameter behavior.

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 (acceptance-test the running PREVIEW) and explicitly contrasts itself with build_audit ('reads the code' vs 'USES the deployed preview like a buyer would'). It also positions itself in the pipeline against build_deploy and build_go_live, so an agent can separate it from build_smoke_test/build_validate without opening any schema.

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 explicit ordering ('after build_deploy, before build_go_live'), an explicit exclusion ('Only the caller's own project PREVIEW, never the live app or other projects'), and a full flow: build_audit -> build_publish -> build_deploy -> build_verify -> fix -> build_go_live. Alternatives and preconditions are named rather than inferred.

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