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

Annotations declare readOnlyHint=false and destructiveHint=false, so the agent knows this produces output rather than mutating the source. The description adds the output shape (ZIP of parts), but says nothing about where the ZIP lands (library vs ephemeral), size/page limits, or whether the original is preserved.

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 sentences, zero filler, with the resource and both modes front-loaded and the return value last. Every clause carries information an agent needs.

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?

With 6 parameters, zero required, and three overlapping file-source options, the definition should say that exactly one file source and one splitting mode must be supplied. That coordination rule is absent, and combined with a nested `file` object it is the main remaining gap; the output schema covers return-value details.

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 67%, and the description specifically compensates for the two undocumented parameters: it gives concrete `ranges` syntax examples ('1-3', '4', '5-9') and names `max_part_mb` as the alternative axis. It leaves the file-source parameters (file_id, file_url, library_file_id) to the schema, which does document them, so this is a solid but not exhaustive contribution.

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 two operating modes plus the return artifact ('a ZIP of the parts'). No sibling does splitting, so disambiguation is implicit rather than stated, which keeps it just below a 5.

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 two modes (explicit `ranges` vs size-capped `max_part_mb`) are surfaced, which implies when each applies, but the description never says whether they are mutually exclusive, whether one is required, or when to prefer split over edit_pages/merge_pdfs. Usage is inferable but not guided.

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