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

With no annotations present, the description carries the full burden and does add real behavioral context: a paid x402 call at $0.0025 USDC per invocation, and a hard limitation to text-layer PDFs (implying failure on scanned/image PDFs despite the schema hinting at OCR). It does not say what happens on a non-text-layer PDF, error shape, or output pagination behavior.

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?

Two tight fragments: capability and constraint first, cost second. No filler, and the most decision-relevant facts (formats, page granularity, limitation, price) are all front-loaded.

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 3-parameter tool with no annotations and no output schema, the description covers purpose, formats, limitation, and cost reasonably well. The gaps are the input-path ambiguity (url vs file_base64), what the returned structure looks like given the 'page by page' claim, and failure behavior for non-text-layer PDFs.

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 67%, near the baseline band. The description maps 'plain text or markdown' onto the format enum, but says nothing about the url vs file_base64 choice — the schema describes url as optionally 'an image for OCR' while the description restricts itself to text-layer PDFs, and mutual exclusivity of the two input methods is never clarified.

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+resource ('PDF to plain text or markdown') with two output formats and page-by-page granularity, which is far more informative than a bare name restatement. It does not, however, differentiate itself from the sibling extract_document or preview_document, leaving the agent to guess at the boundary.

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?

'text-layer PDFs only' is a genuine exclusion that tells the agent when NOT to use this tool, which is more than most definitions offer. But it never names an alternative for scanned PDFs or explains when to prefer extract_document or preview_document, so the routing decision is left implicit.

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