extract_document_data

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description reinforces this by stating 'never modifies the input file' and adds behavioral details beyond annotations, such as 'plain text plus a block count' and 'paragraphs/sheets/slides'. However, it does not address the presence of backup/dry_run options in the schema, which could confuse agents into thinking writes are possible, though this is not a direct contradiction.

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, no fluff. The first sentence front-loads the purpose and modes, the second emphasizes read-only safety, and the third points to an alternative. 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?

For a read tool without an output schema, the description conveys the three modes with examples of what is returned. It also notes the read-only guarantee. It does not enumerate all metadata fields or detailed structure formats, but the information is adequate for a straightforward extraction tool. The undocumented but irrelevant options are a minor gap.

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%, so parameters are self-documenting. The description adds semantic richness by explaining what each mode returns: metadata (author/title/etc.), text (plain text plus block count), and structure (paragraphs/sheets/slides). This goes beyond the schema's minimal 'What to extract' description.

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 reads document data and enumerates specific extraction modes (metadata, text, structure). It explicitly distinguishes itself from compare_documents, which is a sibling tool. The verb 'Read' and resource 'document data' are specific and unambiguous.

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 clear context: it is a read-only operation and never modifies the file. It explicitly names compare_documents as the alternative for comparing two documents. It does not exhaustively list when not to use, but the read-only statement and alternative give sufficient guidance.

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