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

Annotations already cover safety (readOnlyHint=true, openWorldHint=false), and the description adds genuinely non-obvious behavior: output varies with the answers you supply because conditional fields are revealed dynamically. It stops short of describing error behavior for invalid doc_id/state combinations.

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?

Two short sentences with no filler. The core purpose comes first and the conditional-field mechanic follows immediately, so an agent can act on it after one read.

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?

No output schema exists, so the description carries the return-value burden, and it does name the returned field attributes. For a 4-param read-only tool with fully documented schema, this is nearly complete aside from the implicit dependency on list_documents for doc_id values (which the schema itself supplies).

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 the schema already documents lang, state, doc_id, and answers in detail; baseline 3 applies. The description's parenthetical lists returned field attributes rather than parameter semantics, and adds nothing beyond what the schema states about the answers object.

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+resource (retrieve field definitions for a document in a given state) and enumerates what a field contains (steps, ids, labels, types, options, required). It is clearly distinguishable from render_document or validate_document, though it never names those siblings explicitly.

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?

"Pass partial answers to reveal conditional fields" is a concrete usage tip for progressive form completion, but there is no guidance on when to pick this over validate_document or render_document, and no stated prerequisites (e.g. must call list_documents first).

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