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

Annotation Contradiction: readOnlyHint=true implies no side effects or state changes, but the description explicitly states 'Debits 1 credit on ok:true' and mentions updated credit fields in the 200 response body. This is a direct behavioral contradiction with the annotation.

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 dense run-on collection of operational fragments with no sectioning or paragraph breaks. Critical scope information like 'No OCR' is buried at the end, and the telegraphic style makes the tool harder to parse quickly.

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?

For a one-parameter paid API, the description covers endpoint, auth, installation, credit cost, response fields, error format, retry behavior, and testing URL. The only real gap is that the extracted text payload structure is implied by the tool name rather than explicitly described.

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%, and the url parameter already documents the absolute http(s) URL and text-layer requirement. The description repeats the golden URL and adds workflow details, but does not materially extend the meaning of the url parameter itself.

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 'Text-layer PDF extract (POST /pdf)', giving a precise verb, resource, and endpoint. Closing with 'No OCR' further clarifies the tool's exact scope and separates it from potential OCR-based alternatives.

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 provides strong invocation guidance: install via llms.txt, prefer Bearer auth, quote credits before calling, and use the golden URL to verify output. There is no alternative PDF tool among the siblings, but 'No OCR' and the credit workflow serve as practical when-to-use/when-not-to-use indicators.

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