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

Annotations already declare openWorldHint=true and destructiveHint=false, and the description usefully adds that prompts are sent to an external agent endpoint and that responses are judged. However, it is silent on whether the run is synchronous or asynchronous, whether results are persisted, and on latency/cost implications of the outbound calls.

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 tight sentences, front-loaded with the action and scope, with zero filler. Slightly compact given the operation's complexity, but nothing is wasted.

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?

The description covers return values (per-test scores, overall pass rate), which compensates for the absent output schema. But for a six-parameter, open-world, non-read-only operation, it omits whether execution is async and paired with get_agent_eval_results for polling — a real gap an agent needs to plan a workflow.

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?

With 100% schema description coverage, all six parameters are already documented, so baseline is 3. The description restates the criteria dimensions and 'overall pass rate' (tying to pass_threshold), but adds no format, default, or edge-case detail beyond the schema.

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 names a specific verb+resource ('Run a conversation evaluation against an AI agent endpoint') and enumerates the judged dimensions. It is clearly distinct from data-retrieval siblings like get_agent_eval_results, though it does not explicitly differentiate itself from run_adversarial_eval or run_persona_review.

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?

There is no explicit guidance on when to use this versus run_adversarial_eval, run_persona_review, or get_agent_eval_results, nor any stated prerequisites (e.g., test cases must exist in the project). The agent must infer usage from the name and schema alone.

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