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

With no annotations, the description carries the burden and does well: it discloses the async/background model, the queued return state, the polling contract, quota consumption (20/month, 3 trial) and that results are informational and do not change scores. Gaps remain on what happens when the quota is exhausted or how a run fails, but the core behavioral profile is unusually well covered.

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?

Three sentences, front-loaded with the action and return state, then the polling instruction, then cost and side-effect caveats. Every sentence adds distinct information with no repetition of the name or title.

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 7-parameter asynchronous mutation with no annotations and no output schema, the description covers the lifecycle and the cost model well. It stops short of saying what the queued return contains (e.g. the run identifier needed for get_eval_run), which matters since no output schema documents the response shape.

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%, so every parameter including the required idempotency_key, the kind enum, suite_id, server_id and skill_ids is already well documented in the schema. The description adds no parameter-level meaning beyond noting the run counts against quota; 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?

States a specific verb and resource ("Starts an eval run") plus the execution mode ("in the background and returns it queued"), and names the sibling get_eval_run as the follow-up reader. An agent can tell instantly that this is the async kick-off call rather than a read or export.

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 clear usage context: start here, then poll get_eval_run until status is finished, invalid or error. It does not explain when to choose which run kind (paired vs tool_grades) — that is left to the enum description — and states no when-not-to-use conditions beyond the implicit quota limit.

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