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

Annotations already establish readOnlyHint=true and openWorldHint=false, and the description adds meaningful behavior beyond that: it is free and non-AI, lists what it checks, notes that it is the same check exported as check.mjs, and discloses the publish-gating behavior for critical findings. This adds useful operational context without contradicting the read-only annotation.

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 two dense sentences with the core operation front-loaded followed by the critical-finding and write_files guidance. Every clause contributes something useful: what is checked, the export equivalence, and the publish gate.

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 one-parameter read-only check with annotations covering safety and no output schema, the description is largely complete: it explains scope, behavioral impact, and remediation path. It stops short of describing the result format or how to obtain project_id, but the annotation coverage reduces the burden on the description.

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?

There is one required parameter, project_id, but schema description coverage is 0% and the description does not specify its format, where to obtain it, or how it is interpreted. The phrase 'on the project as it stands' only weakly implies that project_id identifies the target, leaving the parameter largely undocumented.

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 states a specific verb and resource: a ship check on the project as it stands. It enumerates the exact classes of issues checked (hardcoded keys, generated SQL/shell, raw HTML, permissive cookies, unauthenticated data-changing routes, SEO misses), which makes the tool clearly distinct from siblings like app_status or check_handle. Naming write_files as the follow-up for critical findings further clarifies its role.

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?

The description gives clear usage context: the check is run before publish/export, critical findings stop a publish until owner confirmation, and those should be fixed with write_files first. It does not explicitly state when not to use it or compare directly against sibling tools such as check_handle, so it falls short of a full when/when-not/alternatives treatment.

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