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

Beyond annotations, the description discloses critical behavioral details: the cost of 1 credit per call, the temporary nature of the download link (15 minutes), and an explicit instruction to always include the link in the reply. These are not present in annotations and significantly help the agent handle the tool's side effects and output appropriately.

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 concise and well-structured. It front-loads the core purpose, then provides the scale mapping, cost, and output handling instruction. Every sentence adds value; there is no fluff or repetition. The critical 'Always include that link' instruction is placed last, ensuring it is not missed.

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 adequately explains the return value (a temporary download link) and how to handle it. It covers cost, defaults, and the scale parameter's semantics. All required inputs are clear, and the agent has enough information to invoke the tool correctly and act on the result. No critical gaps remain.

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?

The schema already documents all three parameters (100% coverage), so the baseline is 3. The description adds meaningful semantic detail for 'scale' by mapping values to DPI (1 is 72 dpi, 2 is 144 dpi), which goes beyond the schema's generic 'Resolution multiplier' and helps the agent set appropriate values. This justifies a score above baseline.

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 verb and resource: 'Renders each page (or the ones in `pages`) as a PNG.' It explicitly states the conversion action and the optional page selection, which distinguishes it from sibling PDF tools like extract_pdf_text or merge_pdfs. 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 conveys the primary use case (converting PDF pages to images) clearly, but does not explicitly name alternatives or state when NOT to use it. However, the context of sibling tools (e.g., images_to_pdf, extract_pdf_text) makes the intended scenario inferable, and the description provides the necessary context without needing explicit exclusions.

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