chrysalide_cancel_task

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

With no annotations provided, the description carries the burden. It adds useful context that the sandbox is preserved for inspection ('La sandbox est conservée pour inspection'), which is a meaningful behavioral disclosure. However, it doesn't state whether cancellation is reversible, what state the job transitions to, or whether results are discarded. Some value added, but gaps remain.

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 short sentences, zero waste. The first states the core action, the second adds a valuable behavioral detail about the sandbox. Efficient and 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?

This is a simple cancellation tool with only 2 params, full schema coverage, and no output schema, so its informational needs are modest. The description covers the core action and a key behavioral detail (sandbox preservation). It's adequate for a task of this simplicity, though it could mention what the cancellation returns or what state the job ends in.

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% (both params documented: job_id as job identifier, reason as cancellation rationale). The description itself adds no parameter-specific detail beyond the schema, so with full coverage the baseline of 3 applies. The 'reason' param's optional nature and purpose is clear from schema alone.

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 the verb+resource: 'Annule un job en cours' (cancels an in-progress job), differentiated from siblings by the action of cancellation. It's specific about what it does, though it doesn't explicitly contrast with sibling tools like get_status or start_task, so a small deduction.

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?

No explicit when-to-use guidance is provided. The tool's purpose implies cancellation of a running job, but there's no mention of when cancel is appropriate versus waiting, whether it can only be applied to running jobs, or any relationship to sibling tools. Usage context is only implied by the name and description.

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