save_workflow

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

The description discloses several non-obvious behaviors beyond the annotations: it refuses invalid saves unless allow_invalid=True, never overwrites by default, renames collisions to '<name> (dartsman)', reports this through result.renamed_from, and replaces only when overwrite=True. The annotation destructiveHint=false is compatible with the default non-destructive path; overwrite is an explicit opt-in rather than an annotation contradiction.

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 dense but every clause adds information: purpose/format, prerequisite/mission, validation behavior, collision behavior, and overwrite semantics. There is no filler or repetition of schema/annotation fields, and the most important purpose is front-loaded.

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 4-parameter tool with an output schema, the description covers the key invocation constraints: prerequisite, validation gating, overwrite risk, and collision naming. The main gap is that workflow_id and name are not explained in the description, so the agent must rely on parameter names and schema type information.

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 descriptions cover 0% of the parameters, so the description must compensate. It does explain the behavior of allow_invalid and overwrite, and the naming behavior around name collisions, but it never explicitly explains workflow_id or that name is the new save name. These are inferable, but the description leaves part of the parameter-load to the agent.

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 identifies the action ('Save the workflow'), the resource ('UI format, with layout/groups/notes'), and the destination ('ComfyUI's workflow browser + session dir'). It does not explicitly name a sibling it is not, but the UI-format qualifier and the mention of session-dir saving distinguish it from export-only or output-saving tools.

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 a concrete precondition ('Run organize_workflow first'), explicitly says this is the deliverable, and explains when validation errors block saving unless allow_invalid=True. It does not explicitly contrast itself with sibling tools such as export_workflow_json or save_output, so the routing guidance is clear but not comprehensive.

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