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

No annotations exist, so the description carries the full burden, and it does well: it discloses that the call is asynchronous (returns a run id, not a result), that runs take minutes, and that tight polling is discouraged. It stops short of stating permissions, cost, or what happens if a run is already in flight.

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?

Four short sentences, each doing distinct work: purpose, parameter branching, return contract with the follow-up tool, and timing/polling advice. The most important facts are front-loaded and nothing is padded.

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 two-parameter async tool with no output schema, the description covers what an agent needs: the return shape (run id), where to get the result, and how long to wait. Only sibling differentiation and failure-mode behavior are absent.

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%, and the schema already explains both projectId and changedAreas including the omit-for-full-suite behavior. The description's parameter guidance largely restates that, so it adds emphasis rather than new semantics; baseline 3 applies.

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: 'Start a QA test run against a project,' which is concrete enough to act on. It does not, however, distinguish this from the sibling start_exploration, which an agent would also plausibly consider when the goal is 'begin some testing.'

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?

It gives explicit conditional guidance for the optional parameter: pass changedAreas to re-test only what changed, omit for the full suite. It also routes the agent to get_test_run for outcomes. The missing piece is when to choose this over start_exploration.

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