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

Annotations only indicate non-read-only and non-idempotent behavior, while the description adds crucial behavioral detail: async execution, immediate run ID return, polling requirements, re-submission warning, and default-to-latest-published-version semantics. This materially helps an agent avoid common asynchronous pitfalls.

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 dense sentences that front-load the core purpose and then cover async behavior, polling, re-submission, and entity defaults. Every sentence earns its place with no redundant filler or schema repetition.

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?

Given the output schema exists and the input schema fully documents all parameters, the description covers the non-obvious operational context: async polling, the bpr_... ID confusion, idempotency concerns, and version pinning defaults. Nothing an agent needs to call 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 the baseline is 3; the description adds value by explaining the entity parameter's default behavior and the accepted version values ('1.2' | 'latest' | 'draft'). It also clarifies the resource scope, which helps the agent understand how entity relates to evaluationSetId.

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 states a specific verb and resource: run an evaluation set against a version of its resource and score results against ground truth. It also distinguishes itself from the many run_* batch siblings and from get_evaluation_run, so an agent can identify it 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?

The description gives clear operational guidance: it is async, returns a bpr_... ID, should be polled via get_evaluation_run with wait:true, and should not be re-submitted while running. It also warns that this is NOT a get-batch tool, preventing a likely misuse, though it does not enumerate broader alternative tools.

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