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

Annotations already declare non-read-only, destructive, open-world, non-idempotent, so the safety profile is covered. The description still adds real value: the staged pipeline (plan, scaffold, write, install, build, test, start on project's port), the budget consumption, and the polling contract with get_build. It does not say what on-disk state a build may overwrite despite destructiveHint=true, which keeps it below a 5.

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 and the usage gate, then lifecycle, return values, and parameter behavior in a logical order. It is dense and runs long in a single block, with the project_id guidance partly duplicating the schema, but no sentence is filler.

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 destructive, open-world agent-launching tool, the description covers cost, pipeline stages, return values (build_id, run_id), polling target, and the project-vs-root branching. An output schema exists, so return-value explanation need not be exhaustive, and nothing required 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 all three parameters are already documented, including project_id's workspace-folder behavior. The description largely restates that and adds only the workflow hint that a project build is followed by deploy; it offers no additional format or constraint detail. 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?

States a specific verb and resource ('Have the on-server agent build a web page, site, app or API from a plain-language goal') and immediately names the sibling alternatives (write_file, exec, start_app, deploy) that do the same job manually. An agent can distinguish this from prompt or deploy without opening any 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?

Gives an explicit when-to-use gate ('Use it only when the user asks for that agent') plus the cost signal ('counts against the AI budget like prompt') and the do-it-yourself fallback. This is exactly the routing information an agent needs before choosing between start_build and prompt/exec.

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