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

With no annotations, the description carries the full burden and does substantial work: it discloses pricing (€0.002 per operation), the billing/auth mechanism (charged to the API key in Authorization: Bearer), a hard limit (up to 200 pages), the encryption standard for protect (AES-256), and a default (quality 70). It does not say whether operations return a new file URL or mutate in place, nor what happens on a wrong password for unlock.

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 dense blocks — capabilities/constraints first, then a parameter glossary — with no filler sentences. It is slightly run-on and would be more scannable as separate operation lines, but nothing is wasted.

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?

An output schema exists, so return values need no prose, and cost, limits, and auth are all covered. The one gap is that zero parameters are marked required in the schema, yet op is clearly mandatory to disambiguate behavior; the description implies but never states that.

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 0%, so the description must compensate entirely, and it does: all seven parameters are explained, including the allowed op values, the pages syntax example (1-3,5), the degrees enumeration (90|180|270), and the quality default of 70. This is meaning the bare schema could never supply.

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 opens with a specific, enumerated verb list against a single resource class: merge, split/extract pages, rotate, compress, protect with AES-256, unlock, info. An agent can immediately tell this is the PDF-manipulation tool and distinguish it from pdf_text (extraction of text) and pdf_sign.

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 maps each operation to the parameters it consumes (pages for split/rotate, urls for merge, password for protect/unlock, quality for compress), which is genuine invocation guidance. It stops short of naming alternatives or exclusion conditions — e.g. it never says to use pdf_text instead for text extraction, or pdf_sign for signatures.

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