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

Substantially exceeds the annotations: it discloses cache/ID semantics ('IDs require identical bytes, extractor version and config'), partial-result behavior ('Missing spans listed'), latency ('Up to 70 s'), cost ('USD 0.02 per started 10-page block... No free tier'), retention ('kept only with output url (24 h)'), and an explicit prompt-injection warning about returned page text. These are exactly the operational facts annotations cannot carry.

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?

Purpose is front-loaded, but the body is a run-on of terse fragments ('output=url links JSON 24 hours; manifest inline..') with a stray double period and duplicated size limits that the schema already states. Most content earns its place, yet the packaging makes it harder to parse than necessary.

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 paid, open-world, non-read-only tool this covers everything an agent needs before calling: input alternatives, page-selection legality, size caps, determinism/ID requirements, latency, price range, retention and data-handling policy. An output schema exists, so return-value explanation is correctly omitted.

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 description coverage is 100%, so the schema already documents url, pages, output, chunk_chars, file_base64 and reading_order, including the enum meanings. The description mostly restates these ('required closed numeric pages', '20 MB URL/10 MB inline') rather than adding syntax or edge-case semantics, so baseline 3 applies.

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 and resource: 'Bundle PDF chunks with page citations,' and the 'No OCR or embeddings' clause narrows what kind of extraction this is. It does not name any PDF sibling (extract_pdf, pdf_extract_pages, paper_digest) to route an agent between them, so differentiation is left partly to inference.

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 input-source guidance ('url or file_base64') and the hard constraint that pages is a required closed numeric selection within 1-100, which implies usage. But there is no explicit when-to-use/when-not or named alternative among the many PDF tools, so an agent must infer the choice.

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