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

Annotations only declare readOnly and closed-world, but the description adds substantial behavioral context: the output is a rasterized first A4 page, low-resolution, preview-watermarked, returned as an embedded base64 resource, plus no auth needed and a 3-per-IP-per-day rate limit. This is exactly the extra context annotations cannot convey.

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?

Front-loaded with purpose, then inputs, output, and cost in tightly packed sentences. No filler; every clause carries distinct information.

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 exists, so the description carries the return-format burden and does so thoroughly (1-page watermarked base64 PDF). Combined with the size cap, sample fallback, and rate limit, an agent has everything needed to call it correctly.

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% so the parameter is already documented, but the description adds a meaningful constraint (up to 50 KB) and clarifies the omit-to-preview-sample behavior, which is more specific than the schema's 'Omit to preview the sample invoice.'

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 specific verb and resource ('show what a document will look like') and immediately frames the scope as a preview rather than a real conversion, which separates it from sibling html_to_pdf. An agent can tell what it produces without opening the schema.

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?

Gives a clear usage context ('before paying or signing up') and an explicit exclusion ('Not for production use'), which routes the agent away from using this as a real renderer. It does not explicitly name the production alternative (html_to_pdf) to send the agent to, so it falls short of a 5.

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