sanitize_docx

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

Annotations declare destructiveHint: true, and the description reinforces the destructive nature by detailing what is stripped and that an audit report is produced. It adds significant context beyond annotations, such as the three modes and the specific metadata removed. No contradiction with annotations.

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 two sentences plus a short list of modes. It front-loads the purpose, then usage, then modes. Every sentence provides value with no redundancy. Highly 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?

Given the tool has an output schema, the description does not need to detail return values. It covers the main behavioral aspects (three modes, audit report, metadata stripping). It could mention handling of invalid files or overwrite behavior, but the input schema provides output_path defaults. Still, it is very complete for a complex tool.

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 description coverage is 100%, but the description enriches parameter meaning by mapping parameters to the three modes (full scrub, keep-markup, baseline). For example, keep_markup corresponds to the keep-markup mode, baseline_path to the baseline mode, and accept_all is used in full scrub. The author parameter is also contextualized.

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 sanitizes a DOCX file by stripping dangerous metadata and producing an audit report. It lists specific items removed (rsids, author names, etc.) and describes three modes, distinguishing it from siblings like accept_all_changes or diff_docx_files.

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?

Explicit usage context is provided: 'Use this before sending documents to external parties.' The three modes give guidance on when to use each (e.g., keep-markup for redline to counterparty). However, it does not directly exclude alternatives or say when not to use; the sibling list provides alternatives but no explicit comparison.

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