choice

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

With no annotations provided, the description carries the full behavioral burden and does so thoroughly. It discloses calibrated probabilities, that the response covers ALL options so near-ties are visible, and the exact JSON return shape including choice, confidence, probabilities, runner_up, model, latency_ms, and usage.

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 description is well structured: a lead sentence, a use-case paragraph, an Args block, and a Returns block. Every sentence contributes useful information, and the most decision-relevant constraints are front-loaded.

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 tool with no annotations, the description is nearly self-contained: it covers purpose, parameters, output, constraints, and exclusions. It does not mention error/validation behavior, such as what happens with fewer than 2 options or malformed option values, which is a minor gap for a tool that otherwise documents its contract well.

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%, but the description compensates for all three parameters: `question` is clarified with a concrete example, `options` is constrained to a mapping of short unique ids to one-line descriptions with a 2-100 count bound, and `context` is marked optional and advised to be short. This adds substantial meaning beyond the raw schema.

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 description states a precise operation: ask Jev to pick one of 2-100 mutually exclusive options with calibrated probabilities, and names typical decision uses like triage, routing, classification, prioritization, and tie-breaking. It is clearly scoped, but it does not explicitly differentiate itself from the sibling `classify` and `score` tools, whose purposes overlap with 'classification' and 'prioritization'.

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 gives explicit when-to-use context ('fast, cheap structured decisions') and clear when-not-to-use guidance ('NOT for open-ended generation or multi-step reasoning'), including an alternative ('use an LLM for those'). However, it does not address how `choice` relates to the sibling tools `classify` and `score`, leaving some selection ambiguity.

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