Check a deployment

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

Annotations declare readOnlyHint and openWorldHint, but the description adds behavior those annotations cannot express: the call blocks for up to 20 seconds, the recommended retry cadence, the realistic total wait time, and the fact that an unchanged redeploy fails identically. That last point is a genuinely non-obvious behavioral warning.

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 what is returned, then retry policy, then failure handling – a logical order with no filler. It is on the long side and repeats the 20-second figure that the schema already carries, which keeps it just short of a 5.

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?

No output schema exists, so the description carries the return-value burden and does it: it names the key fields (`summary`, `error`, `failedStep`, logs) and says how to act on each. For a two-parameter polling tool with a clear failure path, nothing an agent needs 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 description coverage is 100% – taskId's origin ('returned by deploy') and waitSeconds' bounds and default are already documented in the schema. The description restates the 20-second wait but adds no new parameter semantics beyond that, so the baseline 3 applies.

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 and resource ('Progress for one deployment') and enumerates what it returns: status, per-step detail, analyzed spec, warnings and hazards. This distinguishes it cleanly from the sibling `deploy` (which initiates) and `deployment_history` (which lists past deploys).

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?

Explicit when-to-use and how: call it again immediately until status is succeeded or failed, explicitly forbidding pause-based or custom polling loops. It also gives an expected duration ('one to three minutes') and prescribes a failure path: read `error`, `failedStep`, logs, fix the cause, then redeploy.

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