Run Tests

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

The description goes well beyond the idempotentHint annotation by disclosing the exact success response format, the START-UNKNOWN failure mode, and the correct resolution strategy (reusing the same request_id). This is critical behavioral information that an agent needs to handle dispatch reliably.

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?

The description is four concise lines, front-loaded with the core purpose. Every sentence adds value: the action, the success format, and the failure handling. No filler or redundant information.

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 compensates by specifying the response protocol. It covers the main dispatch flow and the transport-failure edge case. However, it does not mention how to check results later (e.g., via run_tests_wait), leaving a slight gap in the overall workflow for a dispatch-only tool.

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. The description adds meaning for request_id by explicitly tying it to the START-UNKNOWN resolution flow, and it mentions run_id and utf_guid in the response, reinforcing the durable identity concept. It does not explain mode or filter beyond the schema, but the added context for request_id elevates it.

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 clearly states the action ('Dispatch Unity tests') and the distinctive outcome ('return their durable identity immediately'). This differentiates it from the sibling run_tests_wait by emphasizing the immediate, async nature of the dispatch.

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 implies usage for asynchronous dispatch and provides operational guidance on handling START-UNKNOWN, but it does not explicitly contrast with alternatives such as run_tests_wait or state when not to use this tool. The guidance is more about handling edge cases than selecting between tools.

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