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

The description goes well beyond annotations by revealing critical behavioral traits: steps run sequentially regardless of depends_on, 'transform' and 'connector' types fail at runtime (so agents should avoid them for actual work), slug derivation from name, and required auth scope. Annotations only show readOnlyHint=false and destructiveHint=false, which are minimal; the description compensates fully with rich, actionable details.

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 front-loaded with the core purpose, then adds essential behavioral nuance. At 5 sentences, it's efficient without being verbose. Minor improvement could be integrating the slug note and auth scope more seamlessly, but the structure is logical and scannable.

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 the tool's complexity (5 parameters, nested steps array, edge cases like non-agent types), the description covers all critical behavioral aspects: execution order, slug usage, type limitations, and auth requirements. It does not need to explain output schema since it exists. The description is complete for an agent to decide and invoke correctly, with no apparent gaps.

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 baseline is 3. The description adds value by explaining the slug derivation ('returned — use it with run_workflow') and clarifying the depends_on caveat (metadata only), which augments the schema. It could further explain parameter interactions (e.g., how 'steps' array constraints relate) or the 'domain' default, but the added context is helpful and not redundant.

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 tool creates a new custom workflow template owned by the caller, with a specific use case ('multi-step pipeline can be built in conversation instead of by hand in the browser'). It differentiates from siblings like 'plan_workflow' (planning) and 'run_workflow' (execution), and the verb 'create' is precise. The description also clarifies that the tool saves the same definition as the web builder, reinforcing its purpose.

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 provides clear when-to-use context (building a pipeline in conversation) and explicitly references sibling tool 'run_workflow' for execution. It briefly notes that steps run sequentially and that 'depends_on' is metadata only, which helps avoid misuse. However, it lacks explicit 'when not to use' guidance or comparison to alternative tools like 'update_workflow_template' or 'plan_workflow', which could further clarify boundaries.

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