workflow_node_add

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It discloses validation rejections (duplicate id, dangling depends_on, invalid cron), the branch/trunk write behavior based on actor, and the default data_dir resolution chain. It does not mention side effects like whether a branch is auto-created or whether the operation is reversible, but the disclosed behaviors are substantial and directly relevant to invocation.

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 a single dense sentence that front-loads the core operation ('向既有 workflow 追加单节点（增量改）'), then packs validation rules and ownership behavior into a compact, readable structure. Every clause earns its place; there is no filler or repetition of schema content.

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 4 parameters, 3 required, nested objects, and no output schema, the description covers the key invocation context: what the tool does, what it validates, and how actor affects the write path. It does not describe the return value or error format, but with no output schema and a clear operation, the description is largely complete. The only notable gap is the lack of detail on what happens when a non-owner writes to a branch (e.g., is a branch created automatically?), but this is a minor omission.

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 100%, so the schema already documents all parameters. The description adds meaning by explaining the actor parameter's role in trunk vs branch routing, and by noting that node.type defaults to 'auto' and visibility defaults to 'open' (though these defaults are also in the schema). The description also clarifies that trigger.schedule accepts sugar macros or five-part cron, which is useful beyond the schema's generic '定时触发周期'.

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 states a specific verb ('追加单节点' = append a single node) and resource ('既有 workflow' = existing workflow), and explicitly frames it as an incremental modification ('增量改'). It distinguishes itself from related workflow tools by naming the operation type and the validation rules (duplicate id, dangling depends_on, invalid cron are rejected). This is a clear, specific purpose that an agent can act on.

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 gives explicit when-to-use context: it is for adding a single node to an existing workflow, not creating or updating the whole workflow. It also provides a clear behavioral rule for who can do what: owner writes to trunk directly, non-owner writes to a branch. This is strong usage guidance that helps an agent decide when to call this tool versus siblings like workflow_update or workflow_create.

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