reject_ai_edits

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

Annotations only say destructiveHint=true; the description goes well beyond by disclosing that the mutation is in-memory and non-persistent, that it sweeps document.xml plus supported side-story parts, that all other revisions are byte-untouched, and that overlap triggers a hard error with code AMBIGUOUS_REVISION_OVERLAP and a structured overlaps list. This is exactly the behavioral context annotations cannot carry.

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?

Three dense sentences, front-loaded with the verb and scope, then persistence, then error behavior. Every clause carries new information, though the final sentence is packed with jargon (side-story parts, normalize_first) that slows parsing 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 mutating, non-persisting tool with no output schema, the description covers the persistence contract, the affected document scope, and the failure mode with its error code and payload. Nothing an agent needs in order 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 100%, so the baseline is 3, but the description adds cross-parameter meaning the schema lacks: revision_ids and author are alternative selectors, and normalize_first is a lossy escape hatch from the ambiguity error rather than a routine flag. The parenthetical on the error path is the main added value.

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 ('reject tracked changes'), the selection keys (revision id or author), the scope ('in the in-memory session'), and the effect on untouched revisions. It also explicitly positions itself against the sibling accept_ai_edits and against save, so the agent can distinguish it without opening a schema.

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 states this tool does not write file_path and that save must be called to persist — a when-to-use and what-to-do-next instruction that would otherwise be a common agent mistake. It names accept_ai_edits as the symmetric counterpart and gives the exact condition (normalize_first) for avoiding the ambiguous-overlap hard error.

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