check_cua_actions

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

With no annotations provided, the description carries the full burden and adds meaningful behavioral context: it is rule-based, does not call an LLM, and does not consume quota. It also discloses the return value shape. The optional audit side effect when session_id is supplied is only mentioned in the schema, not the description, but that is a minor gap because the schema documents it.

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 compact and front-loaded: it states the purpose, the output, the key behavioral trait, and the intended usage context in three dense sentences. There is no filler or redundancy.

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 enumerates the return payload (L0-L3 verdicts, matched_rules, outcome, counts), which compensates for the lack of an output schema. Combined with a fully documented input schema, an agent has enough to call the tool correctly. Slightly more top-level transparency about the session_id audit write would round it out, but that is captured in the schema.

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%, and the input schema already documents all parameters and aliases in detail. The description adds little parameter-level meaning beyond 'submit action trajectory', so the baseline of 3 is appropriate.

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 and resource: risk-grading CUA action trajectories and returning L0-L3 verdicts, matched_rules, outcome, and counts. It is not a tautology and clearly communicates the tool's function, though it does not explicitly differentiate from sibling tools like check_safety or verify_agent.

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 gives a clear applicability context: '用于在 agent 执行前/后做安全自检' (used for safety self-check before/after agent execution). It also notes that the tool is pure rule-based and consumes no LLM quota, which helps an agent decide when to invoke it. However, it does not mention exclusions or explicitly name alternatives among the sibling tools.

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