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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description nonetheless adds meaningful behavior: a 1-to-20 file bound, attach-order semantics, form fields being flattened, no password-protected input, and that output is a single new PDF with a page plan plus a verification check. It stops short of describing failure modes or how the verification check reports mismatches.

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?

It is a single dense paragraph rather than a list, which makes it slightly harder to scan, but the most decision-relevant content (when to use, when not to use) is front-loaded and each clause carries information. There is little outright filler, though the parameter recap partially duplicates 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?

For a 3-parameter tool with full schema coverage, annotations and an output schema in place, the description closes the remaining gaps: input limits, ordering, flattening side effects, unsupported inputs, and the sibling boundary. Nothing an agent needs to invoke it correctly appears to be 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 coverage is 100%, so the baseline is 3, but the description adds usable semantics: file ordering ('attach order'), the page-range grammar ('1-3, 7, 10-end'), skip versus take, and the legal rotation values. It largely mirrors the schema examples rather than introducing new constraints, which keeps it from a 5.

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 concrete, multi-verb statement of scope (merge, combine, join, reorder, subset, delete, rotate) tied to a specific resource (PDF pages). It then explicitly names the sibling it is not for: 'Do not use for splitting one PDF into several files (use split_pdf).' An agent can distinguish merge_pdfs from split_pdf and inspect_pdf without opening a schema.

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?

Use cases are enumerated up front, including the non-obvious single-file mode ('With one file, it can delete, reorder or rotate pages'). Exclusions are explicit and routed to an alternative tool (split_pdf), and unsupported inputs (password-protected PDFs, live form fields, text editing) are called out.

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