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

Annotations indicate readOnlyHint=false and destructiveHint=false, which the description complements by explaining that it returns a new artifact_id, implying a non-destructive operation that creates a new PDF. It adds the page numbering format and the fact that the rest are kept in order. No contradiction with 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: 'Free. Remove the pages you name from a PDF and keep the rest in order.' It then adds necessary details in a single sentence. No fluff; every sentence earns its place.

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 simple deletion tool with an output schema and annotations, the description covers the core operation, page syntax, and return value. It does not need to explain error cases or prerequisites for this simplicity. Complete for an agent to invoke correctly.

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 0%, so the description carries full responsibility. It explains the 'pages' parameter with the 1-based range syntax ('1-2,17') and clarifies that 'artifact_id' is the target PDF ID. Both parameters are fully explained beyond 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 clearly states the verb (remove) and the resource (pages from a PDF), and explicitly notes that 'every other page stays in order', which distinguishes it from extraction or reordering. It differentiates from siblings like extract_pages and reorder_pages by focusing on deletion while preserving order.

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 description implies when to use it (when you want to delete specific pages from a PDF) but does not explicitly contrast with alternatives like extract_pages or provide exclusions. It says 'Remove the pages you name' which is clear, but there is no explicit 'use this instead of X' guidance. The 'Free' note might hint at cost, but that is not a usage alternative.

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