按实时模板绑定首尾帧

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

Annotations declare non-read-only, idempotent, non-destructive, open-world. Beyond those, the description adds genuinely non-obvious behavior: the template's skills, native connections and ordering are preserved, a run_node_key is returned, and the call stops at graph construction rather than triggering generation. That is substantive value on top of the structured hints; only error/failure behavior is unaddressed.

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?

Dense and front-loaded: purpose first, then the inputs mapping format, then behavior guarantees and the return value plus the scope limit. Every clause carries information, though the appeal to a '官网guide' is an external reference that 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 return values needn't be spelled out, and the description still names run_node_key. But for a 5-required-parameter mutation tool with nested object input and zero schema coverage, leaving code/model/prompt/dry_run/operation_id unexplained is a meaningful completeness gap for an agent trying to call it 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 0% across 8 parameters, so the description carries the full burden. It does explain the most important one — inputs maps official template input node_key to existing asset node_key — but code, model, prompt, dry_run (default true), operation_id, project_uuid and canvas_uuid get no treatment at all, so most of the surface remains opaque.

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 gives a specific verb and resource: build multi-input templates (first/last frame etc.) per the official guide, with the explicit scope limit '仅搭图，不生成' (only builds the graph, does not generate). That cleanly separates it from generation-oriented siblings like pavo_submit_task or pavo_apply_canvas, though it never names those siblings directly.

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 conveys usage constraints — bind every input explicitly, never reuse the template's sample assets, follow the official guide — which is real when-to-use guidance. However, it never states when NOT to use this tool or which sibling (pavo_apply_canvas, pavo_create_node, pavo_connect_references) to prefer for adjacent tasks, so the agent must infer the boundary.

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