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

The description adds behavioral detail beyond the annotations: pages use 1-based indexing, supports ranges, repeats, and arbitrary order, and it returns a new artifact_id. This complements the annotations (readOnly=false, destructive=false) by implying a new artifact is created without destroying the source.

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 fairly short but has redundancy: the first and second sentences both repeat 'Keep only the pages...'. This slight repetition could be streamlined, though the action is still front-loaded.

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?

The description is sufficiently complete for a two-parameter tool with an output schema. It covers page syntax, the operation, and the return value. Minor missing detail such as explicit statement about the original artifact being unchanged is implied by 'new artifact_id'.

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 0% schema description coverage, the description compensates by fully explaining the `pages` parameter syntax (1-based, ranges, repeats, order) and contextualizing `artifact_id` as the source PDF. This is essential for correct invocation.

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 action: keeping only named pages from a PDF in the specified order. It distinguishes itself from siblings like delete_pages and reorder_pages by noting that the order of pages can change and that it keeps only specified pages.

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 the tool through its operation ('keep only pages you name, in order'), but does not explicitly state alternatives or when not to use it. It provides context but no exclusions or explicit guidance compared to sibling tools.

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