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

The description confirms the safety profile declared by annotations ('Nothing is queued or changed'), so there is no contradiction. It also discloses the unusual behavior that the response is guidance rather than extracted data, which is exactly the kind of trait annotations cannot express. It stops short of saying whether the call can fail or what the guidance payload contains.

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 sentences, front-loaded with the key constraint ('not available yet') and closed with the safety assurance. Every sentence carries information; nothing is padded.

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 still summarizes what comes back (instructions). For a deliberately stubbed tool the coverage is nearly sufficient; the missing piece is any explanation of the two required identifiers.

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?

Both parameters have 0% schema description coverage, so the description must compensate and largely does not. 'doc_id' is loosely implied by 'from the document', but 'household_id' is never mentioned at all, leaving an agent to guess what household scoping means for a call that performs no extraction.

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 plainly that extraction is not available over this connector and that the tool returns instructions for starting an extraction via the Antevo app or a REST call. The verb+resource is clear and no sibling tool covers extraction, so differentiation is inherent. It loses a point only because the name/title ('extract_document_data') still implies an extraction capability the description then walks back.

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?

Clearly sets expectations: don't call this expecting data, call it to learn how to start an extraction, and it names the two viable paths (in-app or REST call). It does not explicitly say which sibling tool to use instead, but no sibling performs extraction, so the routing gap is minor.

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