flatten_document

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

With no annotations, the description clearly explains the action (accepts changes, strips markup) and the return object. It details the elements modified, providing sufficient transparency for a simple tool.

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 short (two sentences plus return format) and contains no unnecessary information. It could be slightly better structured (e.g., bullet the return), but overall it is efficient.

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 tool with no parameters and a straightforward action, the description covers the purpose and return value adequately. It lacks explicit mention of scope (e.g., headers/footers) but is sufficient for typical use.

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?

The tool has zero parameters, so the input schema provides 100% coverage trivially. The description does not need to add parameter info, earning a baseline score of 4.

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 clearly states the tool accepts all tracked changes and removes revision markup, specifying the exact XML elements handled (w:ins, w:del, w:rPrChange, w:pPrChange). This distinguishes it from sibling tools like accept_all_changes which may not strip formatting changes.

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 does not provide guidance on when to use this tool versus alternatives like accept_all_changes or reject_all_changes. No explicit context for when to accept or flatten is given.

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