create_flow

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

With annotations already declaring non-read-only, non-destructive, non-idempotent, the description adds real behavior: upfront validation across structure, per-node config, node cap, channel compatibility and keyword collisions, with a 422 invalid_definition response carrying errors[] and warnings[]. The draft-only state and the layout side effect on first open are disclosed. It doesn't say whether a failed validation leaves any partial object behind.

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?

Front-loaded with the action and the draft outcome, then the validation detail, then the lifecycle note. Dense but every sentence carries information; the final sentence about the visual builder layout is the least essential and could be trimmed.

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 deeply nested tool with four parameters, nested definition graph, and no output schema, the description covers the creation semantics, the validation surface, the failure signal, and the downstream lifecycle. An agent has enough to call it correctly and interpret a 422.

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 75%, so the schema carries most field-level meaning, but the description adds a layer the schema cannot express: which aspects of `definition` and `channels` are actually validated (per-node config, channel/trigger compatibility, cross-flow and custom-field references). Individual params like name and tag_id get no added meaning, which keeps it off a 5.

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?

States a specific verb and resource ("Create a flow") and immediately narrows the effect to "Creates a DRAFT from a definition", which separates it from publish_flow/activate_flow and update_flow. The reference to GET /flows/nodes tells the agent where the definition schema comes from.

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?

Clear context: use this to create a draft, and nothing runs until publish and activate. It doesn't explicitly route to validate_flow for pre-checks or to update_flow for changing an existing flow, nor does it state when not to use it, so it stops short of full when/when-not guidance.

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