Render PDF

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

The annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, which covers the safety profile well. However, the description carries additional burden for the payment mechanism. It mentions the cost ($0.05 USDC on Base) but does NOT explain the two-step payment flow in the description itself—this is only buried in the _payment parameter description. For a tool that requires a complex payment handshake, this is a significant behavioral disclosure 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 description is a single tightly-written sentence followed by a cost note. Every word earns its place—it states the input, output, and cost in minimal space. No filler or redundancy.

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 tool is moderately complex (6 params, payment mechanism, output schema present). The description covers the core purpose and cost. The output schema exists, so return values need not be explained. The main gap is that the payment flow (two-step process with _payment) is not disclosed at the description level, but this is partially compensated by the schema and the fact that it's discoverable. Given output schema presence and 100% param coverage, a 4 is appropriate.

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 100%, so the schema already documents all 6 parameters with descriptions. The tool-level description adds marginal value by naming the two input modes (html OR url). However, it does not clarify the relationship or precedence between html and url, nor does it explain the payment flow that the _payment parameter requires beyond what the schema says. The schema carries most of the burden here.

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 uses a specific verb ('Convert') with clear resources ('raw HTML or a public URL') and a clear output ('PDF document'). It clearly distinguishes this from sibling tools like document.parse, image.screenshot, and image.ocr. The purpose is immediately obvious and specific.

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 specifies the input types (raw HTML or public URL), which helps with when to use it. It also mentions the payment cost which sets expectations. However, it doesn't explicitly state when NOT to use it or name alternative tools for similar rendering tasks (like image.screenshot for image output), though sibling differentiation is largely implied by the distinct output type.

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