accept_changes

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

Annotations already disclose readOnlyHint=false and destructiveHint=true, so the mutation risk is covered. The description usefully adds the scope ('document body') and the unsupported-marker caveat ('unresolvedRowRevisions remains 0 for supported row markers'), which is genuine extra context, but it does not state irreversibility or whether the result is persisted to disk or requires a separate save.

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, front-loaded with the action and scope, and the second sentence carries the return-value caveat. Dense and largely waste-free, though the 'acceptance stats' clause is slightly vague.

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?

For a single-parameter destructive mutation with no output schema, the description covers scope, the supported-change limitation, and a return-value detail. The main gap is persistence behavior and the boundary against accept_ai_edits, but the destructive annotation already conveys the safety profile.

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?

Only one parameter (file_path) with 100% schema description coverage, so the schema fully documents it. The description adds nothing about file_path semantics (format support wording mirrors the schema), so the baseline 3 is appropriate.

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 ('Accept every supported tracked change in the document body') and narrows scope with 'supported' plus table-row revision handling. However, it never distinguishes itself from the sibling accept_ai_edits/reject_ai_edits tools, leaving the agent to infer which accept variant applies.

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?

No when-to-use guidance is given — no prerequisites, no mention of when to prefer this over accept_ai_edits or how it pairs with extract_revisions/has_tracked_changes. The agent must guess the workflow context.

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