连接参考素材

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

Annotations already declare the write-but-non-destructive, idempotent, open-world profile, and the description usefully confirms the additive behavior ('不会替换已有连接'). However, it never explains the required operation_id, how idempotency is enforced on retries, or what dry_run actually does, which are the behavioral details an agent most needs for a mutation.

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 short sentences, front-loaded with the core action and followed by the payload shape and the routing rule; no filler. It reads slightly telegraphic, packing item fields into one clause, but nothing is redundant.

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 described, and the reference item shape plus first/last-frame routing are covered. Still, for a 6-parameter mutation with a required operation_id and a dry_run flag, the missing explanation of those two controls leaves a meaningful gap.

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%, so the description has to carry parameter meaning. It does well on the untyped references array by documenting source=node_key, optional role=reference/prompt, and media_order, but leaves project_uuid, canvas_uuid, target_node_key, operation_id, and dry_run entirely unexplained in both places.

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 definition opens with a specific verb and resource: adding ordered image/video/audio references to a node. It also names the one sibling that handles the adjacent case (first/last frames must go through apply_template), so an agent can separate the two without opening either schema.

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 gives one explicit exclusion with a named alternative ('首尾帧必须用apply_template') and states that existing connections are not replaced, implying additive use. It does not cover the more general when-to-use question, such as how it relates to pavo_list_connections or apply_canvas, so it stops short of full routing guidance.

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