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

Goes well beyond the annotations by disclosing that the build is private to the account, is deleted on expiry, only works on the local stdio server, and that exceeding wait_ms returns { status: "running", job }. That lifecycle and local-only constraint is exactly the context an agent cannot get from readOnlyHint/openWorldHint.

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-loads the action and its output, then the required follow-up, then the constraints. Every sentence carries information, though the run of three constraints in a row is dense enough that a list would read faster.

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 still states the return value (a build id), the async fallback shape, and the expiry behavior, and covers the local-only limitation. Nothing an agent needs to invoke it correctly 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%, so the schema already documents app, dir, wait_ms, and skip_build. The description adds only the polling hint that a running job can be read later with job_status; it says nothing new about app/dir defaults or skip_build that the schema does not already carry.

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?

Names a specific verb and resource (build the app in this project) and states the full effect: build, upload to the hosted phone for this key, return a build id. The parenthetical tying it to the `shipvo sim` build makes the artifact concrete, and the follow-up open_app call separates it from the sibling that merely opens apps.

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?

Gives a clear precondition — runs only on the local (stdio) server because it reads the project — and prescribes the follow-up step open_app("<app>@build:<id>"). It does not explicitly contrast with siblings like apply_update or export_test, so the agent must infer which to prefer for pure build/upload work.

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