extract_revisions

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description confirms the read-only nature while adding real behavioral detail: how row-level insertions/deletions/format changes are surfaced with scope "row" and ROW_INSERTION/ROW_DELETION/FORMAT_CHANGE records, and that pagination is supported. This goes beyond what the annotations convey.

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 main purpose is front-loaded in the first sentence, followed by necessary detail on row-scope records and pagination. The middle sentences are dense and technical but each carries useful semantics rather than filler.

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, the description carries the burden of explaining return values, and it does so well (before/after text, revision details, comments, row-scoped records). The only minor gap is that it doesn't restate accepted file types (DOCX/ODT, which the schema covers) or the author/date fields' format.

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 100%, so file_path, offset, and limit are already documented with ranges and defaults. The description only notes that pagination exists via offset and limit, adding no syntax or format detail beyond the schema; baseline 3 applies.

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 (Extract) and resource (tracked changes) plus the output shape (structured JSON with before/after text per paragraph, revision details, comments). Clear enough to distinguish from the sibling has_tracked_changes, which only checks presence.

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?

Usage is implied by the purpose but never stated as when/when-not. It does not route the agent to siblings such as has_tracked_changes (to check first) or accept_changes/reject_ai_edits (to act on the revisions), so no explicit selection guidance is given.

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