get_build_status

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

The description says 'Non-destructive', which is valuable given the lack of annotations. It doesn't add context about authentication, rate limits, or the shape of the returned status object; and no output schema exists, so the agent cannot predict return data.

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?

Single run-on sentence with semicolons. It is reasonably concise but contains a minor malformed phrase 'reaches ready (then publish) or failed.'

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?

Without JSDoc or output schema, it is not exposed to describe what a build status object contains, what fields, what possible values; the description assumes one read cmd but not detailed semantics; no contexts.

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?

Input schema has two required params with brief descriptions ('app_id', 'build_id'), but the descriptions are minimal and no extraneous meaning such as formats/constraints is added. Schema coverage is complete, hence baseline 3.

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 uses a specific verb 'Returns' with resource 'status of a build by id', and adds scope ('by id'), and lifecycle behavior (polling until ready or failed). It distinguishes this as a read/poll operation. However, the sentence structure is slightly awkward.

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 specifies when to use it (polling until status is ready or failed) and clarifies the action. It doesn't mention alternatives, but this use case is clearly implied by 'poll until ready (then publish)'.

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