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

With no annotations supplied, the description carries the full burden and does so: it discloses per-page billing at €0.005, that charges go to the API key in the Authorization: Bearer header, and that scanned PDFs are flagged rather than silently returning empty output. That is exactly the kind of cost, auth, and edge-case behavior an agent needs before calling.

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?

It is compact and front-loads the core capability, with cost and parameters following in a predictable order. The parameter list is crammed into a single trailing sentence with dashes, which is dense but still parseable; nothing is redundant.

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?

An output schema exists, so return shape need not be explained, and the description still covers the remaining gaps an agent would care about: cost model, auth mechanism, page-range syntax, table toggle defaults, and scanned-PDF behavior. Nothing essential to a correct call is missing.

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 0%, so the description must compensate, and it documents all three parameters with formats and defaults ('pages: e.g. 1-5 (default all)', 'tables: bool, include tables (default true)'). The one weakness is that it calls tables a bool while the schema types it as a string, which could cause an agent to pass the wrong type.

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 names the exact resource and output form ('text layer of a PDF as Markdown') plus the concrete structural work done (headings by font size, bullets, Markdown tables). It also distinguishes itself from the sibling OCR tool by stating it flags scanned PDFs with no text layer so they can be sent to OCR.

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?

It gives a clear routing condition: if the PDF has no text layer, send it to OCR instead. That implicitly defines when this tool is the right choice, but it does not mention the nearby extraction siblings (table_extract, pdf_tools, doc_convert) or state when this tool is unsuitable for other reasons.

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