safe-docx

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

The description complements the destructiveHint annotation by explaining the specific destructive risk: 'rebuild mode (which destroys table structure)' in the fail_on_rebuild_fallback parameter. It also discloses that checkpoint returns a revisionId, adding return value context not present in the output schema.

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 compact (one sentence with fragments) and front-loads the core action, but its brevity is insufficient for a 10-parameter tool supporting dual platforms. The Google Docs checkpoint/snapshot distinction lacks clear parameter mapping, causing potential confusion.

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 absence of an output schema, the description partially compensates by noting the revisionId return for Google Docs checkpoints, but omits return details for DOCX operations. For a destructive mutation tool with complex parameter interactions, it should clarify the relationship between file_path/google_doc_id and the save format options.

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?

With only 30% schema description coverage, the description fails to compensate adequately. While it implicitly maps to `save_format` (clean/tracked/both) and `google_doc_id`, it leaves 7 parameters undocumented, including `clean_bookmarks`, `tracked_changes_author`, and `tracked_changes_engine`, providing no semantic context for these controls.

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 it saves documents and distinguishes between two distinct workflows: DOCX (clean/tracked outputs) and Google Docs (checkpoint vs snapshot). It specifies what each variant returns or produces, which helps distinguish it from siblings like `read_file` or `compare_documents`.

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 provides internal format selection guidance (clean vs tracked for DOCX, checkpoint vs snapshot for Google Docs) but fails to differentiate from sibling persistence tools like `close_file` or `accept_changes`. It does not state prerequisites like having the document open or loaded.

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