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

Adds context beyond annotations: it is a full replace of the definition, updates require the current version (optimistic concurrency), and already-launched executions keep their existing steps. That last point is a genuinely useful side-effect disclosure for a replacement operation. Annotations already cover the safety profile (readOnly=false, openWorld=false), so the bar is lower, and no auth or permission details are given.

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?

Two sentences, front-loaded with the core action, no padding. The second sentence is dense but every clause (read first, send id and version, conditional form, running executions unaffected) carries information an agent needs.

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 an 8-parameter tool with nested trigger/steps/form objects and no output schema, the description does not explain what a trigger or a step should look like, so an agent still lacks the shape of the most complex inputs. It is adequate at the level of which fields to send, but not complete for correct invocation.

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 must carry the meaning, and it does for most of the 8 params: it names id, version, name, status, trigger, steps and form, and clarifies that id+version are the update mechanism while form is conditional. The 'description' parameter is never mentioned, and the internal structure of trigger/steps/form remains fully 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?

States a specific verb pair and resource: 'Créer ou remplacer la définition complète d'un workflow'. An agent can distinguish it from delete_flow, run_flow, control_run or describe_workflows without opening the schema. The qualifier 'généraliste' is unexplained and slightly muddies which workflow type this targets.

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?

Explicitly gives the update path: read the flow first, then submit id together with the current version. That is real when-to-use guidance tied to a sibling read operation. It stops short of naming exclusions (when not to use it versus save_agent or set_workflow_state).

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