查看运行

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

The description discloses the specific information returned (status, stats, evidence index, errors) and is consistent with the readOnly and idempotent annotations. However, it does not mention potential error conditions (e.g., run not found) or side effects, though as a read-only operation these are likely minimal.

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?

The description is a single concise sentence, front-loaded with the action and resource, efficiently conveying the tool's purpose and data returned without unnecessary detail.

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 simple read operation with one parameter, the description sufficiently covers the core functionality. It does not explain the output schema or error handling, but these are likely inferred from the read-only nature and the presence of an output schema, making it complete enough for typical use.

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 description explicitly states that run_id is used to identify the run ('按 run_id 读取'), giving clear meaning to the parameter beyond the schema's type and minLength. This fully clarifies the parameter's purpose.

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 states that the tool reads run status, statistics, evidence index, and errors by run_id. It uses the verb '读取' (read) and specifies the resource (run) and the data retrieved, making its purpose unambiguous and distinct from sibling tools.

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 does not explicitly mention when to use this tool versus alternatives. It only describes what it does without providing conditions, prerequisites, or comparisons to other tools like 'status' or 'audit', leaving usage guidance implicit.

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