Evaluate agent

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

Annotations only declare readOnlyHint=false and destructiveHint=false, so the description carries the real behavioral load and delivers: 30s–30min runtime, pollable task handle for task-capable clients vs blocking behavior for others, cost preview before the run, and the wait-then-return-scores flow. This is exactly the operational context an agent needs before committing to a long call.

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 duration, followed by client-behavior detail and input requirements. It is tight and well-ordered; the 'give it an agent uuid and a scenario uuid' clause mildly duplicates the schema but reads as a necessary lead-in to the workflow.

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 long-running tool with no output schema, the description still conveys the execution model (async task handle vs blocking), expected latency, cost preview, and the fact that evaluation scores are returned. Nothing an agent needs to invoke 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 description coverage is 100%, so all four parameters are already documented, including num_runs and the 1–240 range on timeout_minutes. The description's mention of timeout_minutes overriding the scenario default restates what the schema already says, adding no new syntax or format detail. Baseline 3 applies when the schema does the heavy lifting.

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+resource chain ('runs an agent against a scenario and evaluates the result end to end') and enumerates what it does (preview cost, run simulation, wait, return scores). It is clearly distinct from get_run_details or preview_run_cost by implication, but it never names a sibling or explicitly excludes one, so it stops short of full sibling differentiation.

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?

Usage is implied rather than stated: the agent is told what inputs to supply ('give it an agent uuid and a scenario uuid') but not when to choose this tool over preview_run_cost or get_run_details. No exclusions or prerequisites are given, leaving routing to inference.

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