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

Annotations already declare this is a non-read-only, non-destructive, non-open-world write, so the safety profile is covered. The description adds only the 'draft endpoint' target context and does not disclose the constraint that stepId/outputName uniqueness or the limited set of supported step types matter, nor anything about failure behavior for a complex mutation.

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?

A single front-loaded sentence with no filler or repetition. It is efficiently written but so terse that it cannot carry the information load the tool requires, so it is concise without being adequately informative.

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 mutation whose step parameter is a deeply nested five-way discriminated union with zero field documentation, the description leaves an agent guessing at required shapes and legal values. The presence of an output schema excuses it from explaining return values, but the input-side gaps remain severe given the schema complexity.

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 0% across all four parameters, and the step object is a five-variant oneOf with no field descriptions at all. The description's hint that step is a 'structured step' gestures at its object nature but supplies none of the variant-specific meaning (method/url for http_request, code for compute, promptTemplate for llm_provider, etc.), so it fails to compensate for the coverage gap.

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 clear verb (Create) and resource (step) scoped to an API draft endpoint, so the general action is legible. However, 'supported structured step' is vague about the five concrete step types (http_request, static_json, compute, llm_provider, transform) that the schema's oneOf enumerates, and it gives no differentiation from siblings step_update, step_reorder, or step_delete.

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?

Provides no when-to-use guidance, no when-not-to-use, and no alternatives. The phrase 'in an API draft endpoint' faintly implies a prerequisite (a draft endpoint must exist), but there is no explicit prerequisite or routing toward step_update/step_reorder for modifying existing steps.

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