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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, yet the description adds real value beyond them: it returns a NEW PDF rather than mutating in place, each stamp is re-verified in the produced file before the link is returned, and it refuses password-protected PDFs and non-Latin scripts/emoji. The one gap is that 'readOnlyHint' on a tool that produces a new file could confuse, and the description does not reconcile that (e.g. whether the original is preserved).

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?

Trigger phrases are front-loaded, which is exactly right for tool selection, but the middle sentence is a long run-on chain of parameters that would read better as a compact list. No sentence is pure filler, though the parameter recap is close to redundant with the schema.

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 an output schema present, return-value detail is unnecessary, and the description instead covers what structured fields cannot: the new-file semantics, post-write verification, and the unsupported-input boundaries. For a seven-parameter nested-object tool, an agent has everything needed to call it correctly.

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% and every parameter already carries an example and default, so the description's recap of format placeholders, six positions, start number, skip and font/margin adds little new meaning. The only marginal addition is clarifying that {n} is this page's number and {total} the last number, which the schema also states.

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?

Opens with a specific verb and resource ('add page numbers to a PDF') and enumerates the concrete user intents it covers, including the cover-page-skip variant. It explicitly names the sibling it is not (stamp_bates_numbers), so an agent can route between the tools without opening the 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 an explicit when-to-use trigger list ('number the pages', 'Page 1 of 10 in footer/header', 'skip numbering the cover page') and an explicit exclusion with the alternative named ('Do not use for Bates numbers (use stamp_bates_numbers)'). Nothing about tool choice is left to inference.

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