Decide TraeCN Approval

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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description expands on them: it reveals that approval revalidates expectedCommand, requires acknowledgeRisk and a locally recorded audit reason, and that denial requires only the decision. It also states the audit logging behavior and the 'never approve beyond scope' rule, which goes well beyond the annotations.

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?

Two sentences with no redundant phrasing. The first sentence states the core action, the second details the mechanics and caveat. Every clause earns its place; the most critical constraints are 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?

With an output schema present and a complex 4-parameter decision tool, the description covers all necessary behavioral context: how to approve (with conditions), how to deny, and the authorization limit. It does not need to restate return values because the output schema exists, and the description leaves no obvious gaps for correct 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?

Schema coverage is 100%, so the baseline for adding value is 3, but the description adds meaningful semantics: it explains why acknowledgeRisk and reason are required for approve, that expectedCommand must be the exact command returned with the pending interaction, and that denial only needs decision. This adds context beyond the schema's bare descriptions.

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 opens with a specific verb ('Approve or deny') and a specific resource ('the unsafe or ambiguous command card currently visible in TraeCN'). It clearly distinguishes this tool from siblings: no other sibling handles approval or decisions, so its purpose is unambiguous. The phrase 'revalidates the exact expectedCommand' further pins down its role.

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 states the condition for use ('unsafe or ambiguous command card') and gives a hard rule ('Never approve beyond the scope the user authorized'). It also clarifies that denial needs only a decision, implicitly indicating the minimal input for that path. It doesn't explicitly name alternative tools, but no sibling serves a similar decision role, so the guidance is sufficient.

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