Cancel or Delete Task

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

Annotations declare destructiveHint=true and non-idempotency; the description goes well beyond that by disclosing refund outcomes per state, that deletion removes files permanently, that terminal Creative Lab tasks cannot be canceled or deleted even with confirm_delete, and the exact response shape. This is exactly the extra context annotations cannot carry.

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?

Front-loads the two-sentence summary, then uses a compact per-type state table. Every line carries a distinct behavioral fact; nothing is redundant with the schema or annotations.

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 no output schema, the description still documents the return object, and it covers the full state machine, refund rules, and confirmation requirement for a destructive 3-parameter tool. An agent has everything needed to call it safely and correctly.

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 is 3, but the description adds real meaning: it explains that task_type is optional because the server resolves the real type, and it maps confirm_delete to the specific states where it is required and where it is useless. That is genuine semantic value beyond the enum list.

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?

States a specific verb pair and resource ('Cancel a queued task, or delete a finished one') and immediately distinguishes the two modes. It is clearly separable from siblings like meshy_get_task_status and meshy_list_tasks, which do not mutate task state.

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?

Gives an explicit when-to-use matrix keyed on task_type and status, including when the operation is refused (IN_PROGRESS non-Creative-Lab tasks) and what to do instead ('Wait until it finishes'). It also states the precondition that confirm_delete requires prior user agreement.

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