创建画布节点

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

The annotations already declare non-destructive, idempotent, and open-world behavior, but the description adds material context beyond them: dry_run is a preview that does not write to the site, and the model code must come from a live list rather than being arbitrary. These are real operational constraints an agent would otherwise miss. It does not describe failure modes or what happens to canvas state when a node is actually created, which keeps it from a 5.

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?

Three short clauses, each delivering a distinct rule (node types, upload flow, model selection, params contents, dry_run), with the most important scoping information front-loaded. Dense but well-structured, with no obvious 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?

An output schema exists, so return values need not be explained, and the annotations cover the safety profile. But for a 13-parameter creation tool with zero schema descriptions, leaving x/y placement, operation_id semantics, and prompt unnamed is a meaningful gap that an agent must guess at.

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% across 13 parameters, so the description has to carry the load, and it only partially does: it explains url/media_type for upload nodes, model, params (duration/count/settings), and dry_run. Positioning (x, y), name, prompt, operation_id, and the uuid fields are left entirely undefined. The added meaning is genuine but covers only a minority of the surface.

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 uses a specific verb (创建/create) and enumerates the resource variants it produces: text/image/video/audio/upload nodes. An agent can tell this is the node-creation tool. However, it never names or contrasts itself with the adjacent pavo_update_node or pavo_list_nodes tools, so the differentiation comes from the name rather than the description.

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?

It provides procedural guidance for the upload path (use the url and media_type returned by the upload call) and for model selection (take the code from the live list), which implies pavo_list_models should be called first. But there is no explicit statement of when to use this tool instead of siblings such as pavo_apply_canvas or pavo_update_node, so the guidance remains implied rather than stated.

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