sanitize_metadata

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

No annotations provided, so description carries the burden. It explains that a copy is written (implying no modification to original), lists specific metadata removed per level. Missing details on permissions, file overwrite behavior, or error conditions.

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 short, scannable paragraphs for levels, then bullet-style args. Front-loaded with main action. No redundant sentences.

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?

Covers purpose, levels, parameters, and output behavior. Has output schema, so return values are covered. Missing some edge cases like error handling or what happens if output_path is same as original.

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 has 0% description coverage, but description fully explains output_path (must be non-empty, destination path), level (1-3, default 1), and redact_authors_as (replacement for level 2+). Adds significant meaning beyond schema.

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?

Description clearly states it writes a sanitized copy of the open document to a specified path. It details three distinct levels of sanitization, distinguishing it from sibling tools like redact_text or scrub_pii.

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 explains when to use each level (1, 2, 3) and defaults, but does not provide guidance on when not to use this tool versus other sanitization or redaction tools among siblings. Implied usage only.

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