agent_eval

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

With no annotations, the description itself carries the burden of behavioral disclosure. It states '只读' (read-only) and enumerates the exact aggregation dimensions and output metrics, which reveals the tool's behavior and return characteristics. It does not cover data-source freshness or empty-result behavior, but the core behavioral profile is clear.

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?

A single dense sentence contains the purpose, aggregation key, full metric list, read-only marker, and intended use. There is no filler or redundant explanation, and the key behavior is front-loaded.

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 parameterless tool with no output schema, the description provides a reasonably complete picture: it is read-only, aggregates by agent, and lists all computed metrics. Minor details such as time range or exact output format are unspecified, but they are not critical for correct high-level selection and invocation.

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?

The input schema has zero parameters, so no parameter-level documentation is needed; baseline for 0 parameters is 4. The description adds context about what the tool operates on (task records) and what it returns, which further helps the agent understand invocation without requiring additional parameter detail.

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 clearly identifies a specific function: aggregate task records by agent and produce five summary metrics (completion rate, average quality, average duration, average retries, satisfaction). It is not a tautology and is distinct from siblings like agent_list or agent_scan, though it does not name them explicitly.

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?

It explicitly labels the operation as read-only and states its intended use case ('供任务路由与选型建议' – for task routing and selection recommendations). This gives clear context for when to use it, even though it does not name alternative tools or provide exclusion conditions.

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