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

Annotations only declare the mutation/safety profile; the description adds the lifecycle behavior that matters: compilation happens in the background in a few seconds, the result is not live until publish_gateway, and issues should be checked with list_gateway_issues. It does not say what comes back from the call (e.g., a gateway id needed for later steps), which is the remaining gap.

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 core action and source-parameter choice are front-loaded, and each sentence carries distinct information (sources, async timing, publish gate, public-API limit, self-host fallback). It is dense as a single paragraph and the self-host routing sentence could be split or trimmed, but nothing is truly wasted.

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?

With no output schema, the description covers the important workflow context – background compilation, the required publish step, and issue checking – which is enough to invoke it correctly. The missing piece is what the call returns and how that identifier feeds publish_gateway or get_gateway.

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 100%, but the description still adds meaning beyond it: the three source parameters are alternatives rather than a set, spec_file_id only applies to files already uploaded via upload_file, and spec is capped at 5 MB. That mutual-exclusivity and ordering knowledge is not in the 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?

Opens with a specific verb and transformation: 'Turn an OpenAPI spec into a hosted MCP server.' It distinguishes itself from siblings by naming list_gateway_issues as the post-compile step and publish_gateway as the go-live step, so an agent knows this is the creation step in a multi-step lifecycle.

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?

It explains exactly which of the three source parameters to use and when: source_url for an https link, spec for pasted text, spec_file_id only for a spec already sent with upload_file. It also states an exclusion – public APIs only – and routes the self-host case to the open-source CLI and docs instead of calling the tool.

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