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

With no annotations, the description carries the full burden and does disclose meaningful behavior: a hard fail terminates the flow, 'answers' is refused on a hard fail, a changed digest, or a malformed answer, auto-completion is capped at 50 USDC, and results are recorded against the caller credential. These are real behavioral traits beyond the schema, though the mode 'single' path and permissions model remain opaque.

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 content is delivered as a single dense run-on sentence with nested parentheticals and no headings or ordering, making it hard to parse and poorly front-loaded. Information density is high but structure and readability are weak, which is a hinderance rather than conciseness.

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 15-parameter, multi-mode tool with no annotations and no output schema, the description covers the overall workflow and refusal behavior reasonably well. Yet key gaps remain (mode 'single', several numeric/credential parameters, undefined internal jargon), so an agent cannot call every path correctly from the description alone.

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 only 13% across 15 parameters, so the description must compensate. It does explain the accepted subject forms (handshake_id, several job_id formats with chain_id, Olas Mech request id, or raw state) and details the 'answers' payload (value, confidence, probabilities) plus model, answered_by, prepare_digest and api_key. However, it leaves price_usdc, execution_id, typesafe_key, chain_id details, record and mode 'single' unexplained, so compensation is only partial.

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 tool clearly involves grading/verdict composition ('grade a subject... code composes the verdict') and returning a receipt plus an anchored decision, which is a recognizable verb+resource. However, the purpose is buried under heavy private jargon ('RUBRIC_v1', 'Jev 1.13', 'TypeSafe node schema', 'assurance-hook job') that an outside agent cannot decode. It also never names or contrasts itself with the sibling judge tools (taifoon_judge_decisions, taifoon_judge_ref).

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 lays out a two-step workflow (mode 'prepare' then mode 'answers') and states prerequisites like using your own TypeSafe credential with no free grade. But the third enum value, mode 'single', is never explained, so the agent cannot choose between all three modes, and no sibling alternative is mentioned.

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