提交生成任务

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

Beyond the annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false, openWorldHint=true), the description discloses quota consumption, a real-world cost gate requiring user authorization, non-blocking submission semantics, and a resubmission prohibition on UNKNOWN. These are meaningful traits the annotations do not convey. It stops short of stating what happens on a failed submit or what the terminal states of a task are.

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?

Four tight sentences with the cost warning front-loaded, followed by submission semantics, then the resubmit rule, then the `regenerate` carve-out. No filler. The shorthand 'UNKNOWN禁止重投' assumes the agent already knows what UNKNOWN refers to, which costs a little clarity.

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?

An output schema exists, so task_id return shape need not be described. For a costly, side-effecting, asynchronous tool the description covers cost gating, non-blocking behavior, and resubmission policy. The remaining gap is parameter-level meaning, particularly operation_id, which is the biggest ambiguity 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 description coverage is 0% and all five parameters are title-only. The description explains only `regenerate`, and does so well by tying it to a terminated original task. The four required parameters (project_uuid, canvas_uuid, node_key, operation_id) receive no meaning at all — notably `operation_id`, whose idempotency/retry-key role is never explained, which matters because the text simultaneously forbids resubmission.

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 names a specific action (submit a generation task), states that it is asynchronous ('立即保存真实task_id，不等待生成'), and implicitly separates it from the polling siblings (pavo_get_task / pavo_sync_task_result). It never names those siblings explicitly, so discrimination relies on inference rather than a direct contrast.

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?

Explicit preconditions are given: call only after the user authorizes model, parameters, and cost range. Explicit exclusions are also given: submit exactly once, never resubmit on UNKNOWN, and use `regenerate` only when the user asks to re-generate and the original task has terminated. This is close to the strongest form of when/when-not guidance.

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