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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so the description only needs to add operational context — and it does: private/local addresses are refused (SSRF guard) and the response is PDF base64, with a ZIP when multiple files are produced. The 10 MB size cap lives in the schema rather than the description, but the behavioral picture is largely complete.

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?

Four short sentences, each carrying a distinct fact — capability, input format, security constraint, output shape — with the primary capability front-loaded. No filler or restated title text.

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 an 8-parameter transformation tool with an output schema, the description covers what matters: the three modes, both input channels, the address restriction, and the return shape (even though the output schema already documents it). Only the range syntax and the third-tier naming parameters are left entirely to the schema.

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?

With 50% schema coverage, the description must carry the unexplained parameters, and it does: it clarifies that 'every' governs chunk size, that 'range' is what gets kept, and that input is either base64 data or a public URL. It adds nothing for 'name', 'filename', and 'mimeType', but the goal-relevant parameters are all covered.

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?

Specific verb (extract/split) plus resource (PDF) plus the three operating modes named up front: page range, single pages, chunks of N. An agent can distinguish this from merge_pdf, compress_pdf, and organize_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?

The mode semantics ('extract a page range', 'single pages', 'chunks of N') imply which option to pick for a given goal, but there is no explicit when-to-use-vs-alternatives guidance. Nothing points the agent to merge_pdf or organize_pdf, nor states when this tool is the wrong choice.

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