draft_api

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false; the description adds the useful clarification that 'no SQL is executed', which tells the agent the tool only generates artifacts. It does not say whether the drafts are persisted anywhere, what happens to prior drafts, or what permissions are needed.

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 that names the outputs first and the safety caveat last; nothing is wasted. It is perhaps too terse given the parameter gap, but as structure it is clean.

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?

No output schema and zero parameter documentation mean the description must carry the load, but it says nothing about the shape of the returned artifacts, where they are written, or how the three required identifiers are used. For a generator with three required inputs this leaves real ambiguity.

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?

All three parameters (path, block_name, package_name) are required yet schema description coverage is 0%, and the description never mentions any of them. An agent gets no hint about format or meaning of 'path' versus 'block_name', so the description fails to compensate for the empty schema.

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States a clear verb ('Return') and three concrete artifacts: PL/SQL stubs, an unpublished ORDS definition and a draft OpenAPI contract. That is far more specific than the name, though it does not relate itself to any sibling tool (the siblings are mostly inspection/planning tools, so differentiation is arguably irrelevant).

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 word 'draft' plus 'unpublished' implies this is for scaffolding an API before publishing it, but the description never states when to prefer it over other tools or what preconditions exist. Usage must be inferred from the artifact names rather than being stated.

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