create_pdf

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It covers key side effects: the 'force' parameter indicates overwrite behavior, 'allow_remote' reveals remote image fetching is opt-in, and it explicitly states it returns metadata plus an inline file. It does not mention error handling or permission requirements, but it provides enough behavioral context for an agent to call it safely.

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 lists each parameter concisely in a consistent format. It is moderately long due to 7 parameters, but every sentence earns its place—no filler. The structure is easy to scan and the argument explanations are tight.

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?

The description thoroughly covers parameters but is vague about the return value ('metadata plus the inline file') without specifying what metadata contains. It also does not mention error cases, idempotency, or whether validation is required before calling. Given the lack of an output schema and the tool's complexity, more detail on return structure and potential failures would be helpful.

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%, so the description is the only source of parameter meaning. It explains each of the 7 parameters with defaults, purpose, and examples (e.g., 'theme: Override the spec theme (e.g. default, report, invoice)'). It even clarifies the spec format via a resource reference. This fully compensates for the schema's lack of descriptions.

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 opens with a clear, specific statement: 'Render a document spec to a PDF and return metadata plus the inline file.' It names the verb (render), resource (document spec), and output (PDF). It distinguishes from siblings like validate_spec (validation) and from_markdown (likely conversion), leaving no ambiguity about what this tool does.

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 implies when to use this tool (to generate a PDF from a spec) but never explicitly contrasts it with validate_spec or from_markdown, nor says when not to use it. It references a spec schema resource, which hints at prerequisites, but there is no direct guidance on alternative selection. This is a clear gap for a tool with siblings.

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