reject_ai_edits

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

Annotations already indicate destructiveHint=true. The description adds beyond that by detailing the scope ('sweeps document.xml and supported side-story parts'), the guarantee of leaving other revisions byte-untouched, and the error behavior with a specific error code and structured response. This enriches the agent's understanding of side effects.

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 description is a single paragraph that fronts the core action and constraints, then details error handling and options. It is dense but efficient. Minor room for improvement by breaking into sentences for readability, but no extraneous content.

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?

Given no output schema and 4 parameters, the description covers the core behavior, error states, and the normalize_first escape hatch. It does not describe return values, but incomplete for a mutation tool with no output schema. Acceptable given the detail on error handling.

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. The description does not add meaning beyond the schema for parameters; it only restates that revision_ids or author can be used, which is already in the schema. No additional syntax, constraints, or examples are provided.

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 uses a specific verb ('reject') and resource ('tracked changes'), clearly stating it restores pre-edit state. It explicitly names the sibling 'accept_ai_edits' as symmetric, distinguishing the tool's purpose from similar operations.

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 description provides clear context: it is the symmetric counterpart to 'accept_ai_edits', and explains the error handling for ambiguous overlaps with an option to normalize. However, it does not explicitly state when NOT to use this tool or offer alternative tools for different scenarios.

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