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

Adds substantial context beyond the annotations: 10 MB size limit, 200-page read cap, which inputs fail and that failures are uncharged, and the pricing model. It even reconciles with the structured data by explaining why readOnlyHint is false ('not marked read-only because each call is charged'), which is exactly the kind of disclosure annotations alone cannot convey.

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?

Front-loaded with the core action and return shape, then parameters, failure modes, use cases, and cost. Every sentence carries information, though the pricing sentence is dense and the description runs long for a four-parameter tool.

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?

With no output schema, the description correctly describes the return payload, covers parameter limits, failure modes, and cost, and ties back to the annotation semantics. Nothing an agent needs to invoke this correctly 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 description coverage is 100%, so all four parameters are already documented, and the description largely restates their ranges ('up to 200', 'cap the output with maxChars'). It adds only marginal meaning (the 10 MB URL constraint) beyond what the schema provides, so the baseline of 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 ('Download a public PDF and return its text page by page') plus the exact return shape (title, author, page count, character counts). This is clearly distinguishable from siblings like extract, extract_rendered, and screenshot, which an agent can now tell apart without opening schemas.

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?

Gives concrete when-to-use guidance ('read papers, invoices, reports and manuals into an agent's context') and explicit failure conditions (scanned PDFs without a text layer, encrypted files, non-PDF URLs). It stops short of naming a sibling alternative or stating when NOT to use it versus extract_rendered.

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