ask_choice

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds real behavioral context beyond them: selection is probabilistic, produces a probability distribution and a utility margin, and depends on active utility profiles. It does not explain how state_pack or utility_profile resolution affects determinism, which is the one remaining ambiguity.

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 sentences, correctly front-loaded with the core action and the sibling-differentiation rule. The return values are stated twice ('with probability distribution and utility margin' and 'Returns selected option ID, probability distribution, and utility margin'), which is redundant but not damaging.

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 no output schema, the description usefully enumerates return values, which is necessary. However, for a tool with nested objects and a 5-parameter signature involving an opaque 'StatePack' and 'utility_profile override', the description never explains what those are or how they influence the choice, leaving conceptual gaps for a non-obvious domain.

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 carries parameter meaning and the baseline is 3. The description restates the 16-option cap (already expressed as maxItems and in the schema text) and adds nothing further about 'project', 'state_pack', or 'utility_profile'.

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 and resource ('Select 1 option from a discrete set of alternatives') and adds the scope constraint 'N <= 16' plus what it produces. It explicitly distinguishes itself from the sibling 'classify' by contrasting decision-under-utility with entity categorization.

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?

Gives an explicit selection rule: use ask_choice rather than classify 'when choosing the best action or alternative under active utility profiles rather than categorizing an entity.' That covers the most confusable sibling, but other decision-oriented siblings (ask_score, ask_noul, evaluate_situation) are not addressed, so the routing guidance is clear yet incomplete.

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