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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, and the description adds meaningful context beyond them: $0.001 per call, no account/OpenRouter required, a 20-question batch cap, and the fact that answers are calibrated probabilities rather than generated text. Error behavior and rate limits are still unstated.

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 front-loaded sentences that establish scope, cost and a sample endpoint with little waste. The marketing parenthetical 'Powered by Jev (TypeSafe System One)' and the sample-endpoint plug are the only soft spots.

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?

With an output schema present, return values need no explanation, and the description covers the key operational facts: state token cap, question cap, question types and where to find criteria shapes. The only gap is guidance on when to prefer this over a sibling tool.

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 100%, so the baseline is 3, but the description adds real meaning by mapping the three abstract type tokens ('noul', 'choice', 'score') to yes/no, multiple-choice and ordinal-scale questions, and by clarifying that all questions share one state and that criteria shapes live in /decide/sample.

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 (ask typed questions), resource (one shared piece of context), and the distinctive output (real probabilities, not generated text). It is clearly distinguishable from sibling text-generation or lookup tools like summarize or fact_check without opening any 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?

Usage is implied — batch multiple probability judgments over a single context in one call — and the 'not generated text' phrasing implicitly contrasts with LLM-based siblings. But it names no alternative and gives no explicit when-to-use or when-not-to-use conditions.

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