accept_ai_edits

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

Annotations only supply destructiveHint=true; the description adds substantial behavior beyond that: the operation is in-memory and non-persisting, which document parts are swept, and the AMBIGUOUS_REVISION_OVERLAP hard-error with a structured overlaps list. This is exactly the context a mutation tool needs.

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?

Dense but front-loaded: the core action and the persistence caveat come first, then targeting, then scope, then the error case. Every sentence carries new information, though the error/overlap sentence is heavy enough to slow scanning slightly.

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 destructive mutation with no output schema, the description covers persistence implications, targeting modes, affected parts, and the failure mode. Nothing an agent needs to invoke it correctly 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 already 100%, so the baseline is 3. The description still adds value by clarifying that revision_ids are w:id values, that author is a convenience alternative, and that normalize_first is best-effort with no byte-identical promise — semantics that go beyond the schema wording.

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?

Opens with a specific verb+resource: 'Selectively accept tracked changes by revision id or author in the in-memory session.' The 'selectively' and 'leaving all other revisions byte-untouched' scope makes it clearly distinct from the siblings accept_changes and reject_ai_edits.

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?

Explicitly routes the agent: use revision_ids for specific revisions, author for a whole actor, and call save to persist since this tool does not write file_path. It also names the normalize_first fallback condition, so the agent knows when to reach for each option.

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