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

With no annotations provided, the description carries the full burden of disclosing behavior. It reveals that this is a partial patch (only included fields change), and it warns about a specific behavioral trap: changing triggerType without triggerEvent can leave the workflow in an inconsistent state. It does not explicitly mention permissions, reversibility, or response format, but for a patch tool, the provided information is valuable and largely sufficient. The lack of more detail on side effects prevents a 5, but it is well above the minimum.

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 compact and front-loaded: the core action and the partial-update rule come first, followed by concrete use cases and the alternative tool. The NOTE is appended for an important edge case. Every sentence adds value, and there is no redundancy. It is appropriately sized for the tool's complexity.

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?

Given 8 parameters, nested objects, an enum, and no output schema, the description covers the essential operational points: partial update semantics, common use cases, the distinction from pause/resume siblings, and the trigger consistency warning. It does not discuss the response format (no output schema is given) or error conditions, but an agent can call the tool correctly with the provided guidance. It is not fully exhaustive, but it is sufficiently complete for a patch operation.

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 only 25% (only id and triggerType have descriptions), so the description must compensate. It does by tying the listed use cases to parameters: 'tweaking step config' (steps), 'updating the trigger event' (triggerEvent), 'switching trigger types' (triggerType), and 'rewording the name' (name). It also advises keeping triggerType and triggerEvent consistent. It does not explain every parameter (e.g., condition, description, triggerConfig), but the general rule 'Only include fields you want to change' covers the partial-update semantics and gives enough context for the most critical fields.

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 states the action ('Patch a workflow') and the resource (workflow), and then lists specific use cases: tweaking step config, updating the trigger event, switching trigger types, and rewording the name. It also distinguishes itself from siblings by explicitly naming workflows_pause / workflows_resume as the preferred tools for toggling active/paused state, so an agent can confidently select this tool for partial updates.

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 opens with 'Only include fields you want to change,' which is explicit guidance on the partial-update semantics. It goes further by naming alternatives ('To toggle active/paused state, prefer workflows_pause / workflows_resume') and includes a critical NOTE about triggerType and triggerEvent needing to be passed together to avoid an inconsistent state. This is exactly the kind of when-to-use and when-not-to-use guidance an agent needs.

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