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

Annotations only signal mutation (readOnlyHint=false), but the description adds rich behavioral disclosure well beyond that: the run may return status 'running' with a runId and that this is normal and should be polled via get_split_run; raw text input is unsupported because splitting is page-based; child file materialization produces a fileId usable in other tools; and results may carry llmContext guidance to follow. No contradiction with annotations exists.

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?

Seven sentences, each carrying distinct information: core function, positioning, mutual-exclusivity constraint, output shape, input limitation, async behavior, and result guidance. It is dense rather than padded, and front-loads the core function first. A small amount of redundancy with schema text (type: 'other', exactly-one-of) keeps it from a 5, but for a 9-parameter tool with async semantics this length is justified.

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 the tool's complexity (9 params, nested objects, async runs, output schema present), the description covers everything an agent needs that isn't already in structured fields: when to use it, the splitter-or-inline-config decision, the type 'other' requirement, page-based limitation, runId polling behavior, the fileId handoff to other tools, and llmContext handling. The schemas cover parameters and return values, so nothing essential is missing.

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. The description adds genuine value on top: the 'Raw text input is not supported — splitting is page-based' note corrects a false affordance in the schema (file.name mentions 'text inputs'), and the prominent 'Provide exactly one of splitter or config' reinforces a critical constraint. Some content duplicates schema text (the type: 'other' requirement), which prevents a higher score.

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 opens with a specific verb+resource pairing: 'Divide a combined file... into typed segments with page ranges', with concrete examples (scanned invoice bundles, merged PDFs of statements). It also differentiates itself from siblings by positioning split as the first step before parse/extract, which separates it from run_split_batch and the get_* inspection tools.

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 gives explicit situational guidance: it is 'the right FIRST step to locate one document or section inside a larger bundle — split, then parse/extract only the relevant segment instead of processing the whole file.' This clearly states when to use the tool. However, it never names alternatives or exclusions (e.g., when to reach for run_split_batch for bulk processing instead), so guidance stops short of being fully explicit.

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