pdg_cook

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

Without annotations, the description carries the full burden. It discloses the in-process handle lifecycle (valid only in process, invalid after server restart), the blocking polling behavior until terminal state or timeout, and the effect of blocking=True. This is meaningful behavioral context beyond the schema.

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 two concise sentences, front-loaded with the core purpose and then key behavioral details. Every word adds value, with no redundancy or filler.

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?

For a tool with no output schema and no annotations, the description covers the essential behavioral aspects (handle, blocking, timeout) but lacks parameter explanations and expected return format. It is adequate for a high-level understanding but leaves out details that could impact 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 the description does not explain node_path or ctx. Only blocking=True is mentioned, offering partial clarity for that parameter. The semantics of the required parameters are left entirely to the agent, which is a significant gap.

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 tool launches a PDG/TOPs cook and returns a handle. The verb '启动' (launch) and resource 'PDG/TOPs cook' are specific, and the mention of returning an in-process handle distinguishes it from sibling tools like pdg_status or pdg_cancel.

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 provides context about blocking behavior and handle validity, implying when to use it (for cooking PDG graphs). However, it does not explicitly state when not to use it, nor does it reference alternatives like cook_node for regular nodes. Guidance is present but not fully explicit.

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