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

Annotations already cover the safety profile (non-destructive, idempotent, open-world), so the bar is lower. The description contributes the zip return format for ranges, but "Uses one render" is unexplained jargon and it never says where output files go or what is returned for the non-ranges modes.

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 tightly packed sentences, front-loaded with the mode list, with no filler. The trailing "Uses one render" fragment is cryptic and could have been dropped or clarified.

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 4-parameter, nested-object tool with no output schema, the description covers mode selection and the zip case but omits precedence when multiple of pages/ranges/every are supplied and does not describe the return for the single-PDF and chunk cases. Adequate but with clear gaps.

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 meaning the schema lacks: it ties each parameter to output cardinality (pages -> one PDF, ranges -> one file per range in a zip, every -> chunks of N). That mapping is genuinely useful parameter context rather than a restatement.

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 ("Split a PDF") and enumerates the three operating modes, so an agent immediately sees the scope. It does not name or contrast with siblings such as merge_pdfs or compress_pdf, leaving differentiation to inference from the verb.

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 three clauses effectively route the agent between modes: pages for a single extract, ranges for one PDF per range (zip), every for fixed-size chunks. It gives no statement about prerequisites, error cases, or when another tool (e.g. merge_pdfs) is the better choice.

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