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

Annotations cover the safety profile (readOnly, non-destructive), and the description adds real value beyond them: the status vocabulary, that failed deploys carry error_explained and retryable, and that the url survives redeploys unless the address changes. It stops short of describing the overall response shape, but the output schema carries that.

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 purpose, then the watch_deploy preference, then output caveats, so the most important routing information appears first. Five dense sentences, all informative, though the url/machine_url guidance could be tightened slightly.

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?

An output schema exists so return values need no full explanation, yet the description still flags the fields an agent must act on (url vs machine_url, error_explained, retryable) and the latency expectations. Nothing needed to call it correctly or safely is missing.

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% and the single project_id parameter is fully documented there, so the description only restates 'by project_id' without adding format or sourcing guidance. Baseline 3 is appropriate when the schema does the work.

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 (get), a specific resource (one project), the key (project_id), and enumerates what comes back: status values, url, health, host machine. An agent can distinguish it from list_projects (one vs many), get_project_logs (status vs logs), and watch_deploy (poll vs wait) without opening a 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?

Explicitly routes between siblings: after deploy_project prefer watch_deploy, and poll this only if watch_deploy is unavailable, with expected latency (1-3 min, up to ~12). It also gives output-handling rules: give the user the url, never hand out machine_url.

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