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

readOnlyHint already covers safety; the description adds plan caps, deploy history, resources.history sampling, and the caveat that metrics may be absent on stacks without the collector. It loses a point for the garbled 'NaNalso' and no explicit auth or rate information, but it is much richer than the annotations alone.

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-loads purpose and usage, and the plan-cap detail is useful. However, it is a dense run-on sentence with nested parentheticals and the garbled 'NaNalso' reduces 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?

With no output schema and 0% schema description coverage, the description must carry more burden. It gives useful output context and caveats, but omits the since parameter entirely and the ambiguous 'NaNalso' leaves a gap for a debugging 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?

Schema description coverage is 0% for two parameters. The description clarifies that omitting project returns all caller projects and that project accepts an id or slug, but since is never mentioned, leaving its format, units, and window semantics 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?

States account-wide or per-project stats for debugging, and names specific content: live CPU/mem vs plan caps and deploy history. It does not explicitly differentiate from get_status/account_status, but the scope and resource are clear.

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?

Explains the account-wide vs per-project choice via the project parameter and labels the tool for debugging. However, it gives no when-not guidance or explicit alternatives among sibling status tools.

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