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

With no annotations, the description carries the full burden and does well: it discloses that read_file cannot decode the binary zip format, that failure surfaces as isError with an honest note, and warns against inventing content. It omits permission or size/pagination constraints, but the failure mode and the anti-hallucination rule are the important behavioral facts.

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, front-loaded with the purpose and output shape, followed by the sibling comparison and the failure contract. Every sentence earns its place with no repetition of structured fields.

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?

An output schema exists, so return values need not be spelled out, and the description already covers the error path. The remaining gap is the undocumented required parameters, which leaves the agent guessing at how to construct the call.

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 0%, so the description must explain that project_id identifies the project and path is the docx location within it; it says nothing about either. 'Path' is partially inferable from the tool's domain, but project_id is entirely undefined in both schema and 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?

States a specific verb and resource ('Read the TEXT CONTENT of a Word document (.docx)') and scopes the output to headings, paragraphs, tables and lists in document order. It explicitly distinguishes itself from read_file, so an agent can select it without opening the schema.

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?

Names the alternative (read_file) and the condition that should route to this tool ('when the user asks you to convert or reference a Word document'), plus the reason read_file fails. It does not address the other plausible sibling, render_docx_preview, leaving some ambiguity on when to preview versus extract.

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