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

Annotations only declare readOnlyHint and openWorldHint, leaving the substantive behavior to the description, and the description delivers: it defines each app_health status (answering, not_answering, checking, paused), the two-minute failure threshold, and the cause semantics of 'problem'/'ai_text'. It stops short of describing pagination, caching, or what happens for a project that hasn't been deployed, but the added context is well beyond the annotations.

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 payload sentence is front-loaded and information-dense, but the app_health passage sprawls into a long run-on sentence with parenthetical asides and typos ('fline', 'fline is putting a new version online'), making it harder to scan than it needs to be.

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, the description must explain the returned fields, and it does so thoroughly for status/app_health, the most operationally important part of the response. It leaves the required project_id undefined and says nothing about the shape of the onboarding/questions/secrets sections, so it is strong but not fully complete.

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% and the description never mentions project_id or its format (slug vs UUID), so the single parameter carries no semantics anywhere. The narrative is entirely about return values, so the description does not compensate for the coverage gap.

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+resource ('The project's full state') and enumerates what that state comprises: onboarding stage, runtime state, open questions, missing secrets, credential warnings, app_health. That is concrete and distinguishable in substance, but it never acknowledges the sibling get_project_detail, which an agent could easily confuse with this tool.

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?

There is an implicit routing cue for the failure case ('read get_logs kind=runtime and fix the app'), which is genuinely useful guidance about what to do next. However, there is no explicit statement of when to call this versus the many sibling state/config tools (get_project_detail, get_config, get_usage), so selection guidance is only partial.

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