safe-docx

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

Annotations declare read-only safety, so description adds valuable behavioral context: token limits (~14k), pagination metadata structure (has_more, next_offset), and default truncation behavior. Missing: mutual exclusivity of file_path vs google_doc_id.

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 sentences efficiently structured: 1) Core function, 2) Output constraints/metadata, 3) Pagination instruction. No redundancy or filler; every sentence 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?

Adequate for a read operation with annotations covering safety profile, explaining pagination mechanics. However, gaps remain: no explanation of format options, node_ids purpose, or mutual exclusion logic for file sources given zero required parameters.

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 71% (5/7 params described). Description adds semantic relationship between offset/limit and pagination, but fails to compensate for undocumented parameters: node_ids (no schema description, no description text) and format enum values ('toon', 'json', 'simple' unexplained).

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?

Specific verb 'Read' plus specific resources 'DOCX or Google Doc' clearly defines scope. Distinct from sibling tools like grep (search), get_comments (metadata), or insert_paragraph (write operation).

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?

Provides pagination guidance ('Use offset/limit to paginate') but lacks explicit when-to-use distinctions versus siblings like grep (when to search vs read full content) or get_file_status (when to check status vs read content).

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