reject_revisions

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

With no annotations provided, the description carries full behavioral disclosure, and it does this well: it reveals auto-backup behavior, that backup=False only skips rotation, that the save is atomic and validated, and that the tool refuses documents open in Word. It stops short of stating irreversible consequences beyond the backup mechanism, but the disclosed behaviors are substantial.

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 clauses convey the core action, scoping, backup behavior, safety guarantees, and a hard failure condition without filler. The main verb and action are front-loaded, and every clause earns its place.

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 the 3-parameter schema and presence of an output schema, the description covers the essential execution context: scope, backup semantics, save guarantees, and an important file-lock refusal. It could mention what 'validated' means or compare to accept_revisions, but for this tool's complexity it is close to complete.

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?

Although schema description coverage is listed as 0%, the description actually adds meaning to the author and backup parameters: 'one author's only' maps to author, and 'backup=False skips rotation only' clarifies a subtle default behavior. file_path is not described, but its purpose is self-evident from the schema and required status.

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 opens with a clear verb and resource: 'Reject tracked changes.' It also scopes the operation to all revisions or one author's, which tells an agent exactly what the tool acts on. It does not explicitly name the sibling accept_revisions, so it misses the differentiation needed for a 5.

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 gives no explicit guidance on when to choose this tool over accept_revisions or revision_summary. The scope options ('all of them, or one author's only') imply usage, but there is no 'when not to use' or pointer to an alternative.

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