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

Beyond the annotations (readOnlyHint=false, idempotentHint=true), the description adds meaningful context: credit cost per call, that cost is independent of output count, and that the result is a temporary download link valid for 15 minutes. This helps manage agent expectations around side effects and output lifetime, and nothing contradicts the annotations.

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?

The description is compact and front-loaded with purpose, then examples, then cost, then output details. The only flaw is redundancy: 'One credit regardless of how many files come out' and 'Costs 1 credit per call' say nearly the same thing twice.

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?

Given there is no output schema, the description appropriately explains the return is a temporary download link and its validity. It covers purpose, input format, indexing, output count, cost, and link expiration. A minor gap is not specifying whether multiple output PDFs are delivered as a zip or list through the link.

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?

The schema already documents both parameters and their examples, so the baseline is 3. The description adds value by clarifying that pages are 1-indexed and introducing the per-page enumeration pattern ('1,2,3'), which is not explicitly in the schema.

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 leads with a specific verb and resource: 'Split a PDF by page ranges.' It immediately states the output ('Creates one PDF per range') and clearly distinguishes itself from sibling tools like merge_pdfs by the essential opposite operation.

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 provides concrete examples of valid range inputs ('1-3,5,7-9'), explains 1-indexed pages, and gives a pattern for one-file-per-page. While it doesn't explicitly name alternatives or exclusions, the usage context is clear enough for an agent to select this tool for splitting.

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