Evaluate agent

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

Discloses blocking nature (30s–5min), cost preview, simulation run, wait, and return of scores. Also mentions optional timeout override. Annotations are minimal (readOnlyHint: false, destructiveHint: false), so description adds useful behavioral context, though it omits whether the run is saved or side effects.

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?

Two sentences, front-loaded with core function, second sentence adds parameter guidance. No redundant words; every sentence adds value.

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?

No output schema, so description should describe return values more thoroughly (e.g., what scores are returned). Also misses mentioning the num_runs parameter entirely. Leaves gaps for a blocking evaluation 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 baseline 3. Description adds workflow context (preview cost, run, wait, return scores) that enriches parameter understanding beyond schema descriptions. However, it does not detail num_runs parameter.

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?

Description clearly states the verb 'runs and evaluates', the resource 'agent against a scenario', and distinguishes from siblings like 'delete_scenario' or 'preview_run_cost' by specifying it does full end-to-end evaluation blocking until completion.

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?

Implies usage via 'Give it an agent uuid and a scenario uuid', but no explicit when-to-use or when-not-to-use compared to alternatives like 'preview_run_cost' for cost-only queries. No exclusions or prerequisites stated.

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