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

Annotations contain only a title and no readOnly/destructive hints, so the description must carry the behavioral burden. It does so well by disclosing that the operation is queued, durable, survives server restarts, returns an ID and status URL, and supports retry idempotency via request_key. It does not cover permissions, failure modes, or cancellation, but the main behavior is transparent.

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?

Three dense sentences convey the core action, return contract, status retrieval path, retry guidance, and durability guarantee. There is no filler or redundant restatement of the title.

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?

For a tool with only one required parameter and no output schema, the description is complete: it explains what is returned, how to check progress, how to retry, and that the build is durable. An agent has enough information to invoke it correctly and proceed to the next step.

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%, so the schema already clearly explains both parameters. The description reinforces the retry semantics of request_key and adds durability context, but it does not add meaning beyond the schema for the prompt parameter. Baseline 3 is appropriate.

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 opens with a specific verb and resource: 'Queue a durable app build'. It also states exactly what the tool returns immediately (an ID and status URL). This clearly distinguishes it from apps_buildstatus and other apps_* siblings because it frames apps_build as the asynchronous creation step.

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 gives clear workflow guidance: use BuildStatus to retrieve progress and the completed app, and reuse request_key on retries. It does not explicitly contrast apps_build with apps_create or apps_edit, but the async build-then-status routing is explicit enough for an agent to know when this tool is the right entry point.

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