Document info

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds that the tool surfaces comments, tracked changes and optionally structure, which is useful beyond the annotations, but it says nothing about cost, size of output, or behavior when multiple input paths are supplied.

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?

A single sentence that front-loads the returned data and appends the optional structure mode; every clause names concrete artifacts. It is dense but avoids redundancy, though the noun-list opening delays the reader from knowing what action is performed.

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 no output schema and 25% parameter coverage, the description should explain the input_dir/input_path/input_paths distinction and the fact that up to 200 paths can be batched, but it does not. An agent still cannot tell whether this handles one document or many, or what the path parameters mean.

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 description coverage is only 25%: input_dir, input_path and input_paths are undocumented in both schema and description. The description does clarify what 'structure' means (headings, paragraph styles, lists, tables with cell texts), which usefully expands on the schema's terse 'blocks (style, text, tables)' for include_structure, but three of four parameters remain opaque.

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 enumerates exactly what the tool returns (pages, words, paragraphs, sections, comments, tracked changes, properties) and offers an optional structure mode, so the resource and output scope are unambiguous. It never states a verb and does not distinguish itself from siblings like extract_text or render_pages, which also read document content.

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 phrase 'to understand a document before editing it' implies the correct usage context (pre-edit inspection) and implicitly pairs it with edit_document. However, no alternatives are named and no conditions are given for choosing this over extract_text or render_pages, leaving routing to inference.

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