start_package_build

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

Adds substantial context beyond the annotations: the build runs as a real external process taking minutes, the call returns immediately, polling is required, and a duplicate build is honestly refused rather than silently queued. This is exactly the behavioral disclosure that matters for a long-running destructive operation.

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 core action and is well-structured, though the verbatim command line and Returns block make it longer than strictly necessary. Every sentence still carries operational value, so no severe bloat.

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 an async build tool with no output schema, the description compensates by stating the return fields, the polling requirement, and the concurrency guard. An agent has everything needed to call it and handle the result correctly.

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 baseline is 3, but the description maps each parameter to its concrete CLI flag (-platform, -clientconfig, -archivedirectory) and shows the default build behavior (-cook -allmaps -build -stage -pak -archive), adding meaning beyond the raw schema.

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 ('Starts an asynchronous project package build (BuildCookRun) via UAT') and distinguishes itself from its siblings get_package_build_status and cancel_package_build by role. An agent knows exactly what operation this performs without opening the 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 the agent to get_package_build_status for progress/outcome and describes the guard that refuses a second concurrent build. It gives clear usage context but does not state when-not-to-use beyond the in-flight refusal case.

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