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

The description adds significant behavioral details beyond annotations: extracting text layer, scanned PDF returns a needs-OCR notice, pricing per document, idempotencyKey ensures no double-read/billing, and blocking private URLs. No contradictions with annotations.

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 moderate-length paragraph of 5 sentences. It is front-loaded with the main purpose and contains no fluff, but could be slightly more concise by removing redundant phrasing like 'never double-read' which is implied by idempotent.

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?

Given the presence of an output schema and 100% parameter coverage, the description completes the picture with critical behavioral notes (scanned PDF handling, pricing, idempotency behavior). No 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?

With 100% schema coverage, baseline is 3. The description adds value by explaining that private URLs are blocked and that idempotencyKey prevents double-billing, which is not apparent from the schema alone.

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 explicitly states the tool reads a PDF and returns text as markdown or plain text, accepts URL or base64, and handles scanned PDFs with a notice. It also positions itself as the canonical ingestion tool, clearly differentiating from its sibling 'generate_pdf'.

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 clearly states it is for reading PDFs, but does not explicitly list when not to use it or alternatives beyond the sibling. However, it notes that private addresses are blocked, which provides a usage constraint.

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