reaction_available

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

With no annotations provided, the description carries the full behavioral disclosure burden. It clearly states behavioral rules: Reactions refresh at the start of the creature's own turn (not the round), are usable on that turn, and are prevented by Incapacitated and conditions that include it (Stunned, Paralyzed, Petrified, Unconscious). It also discloses rejection behavior for unknown or non-condition names, which is critical for error handling. It doesn't describe return values, but an output schema exists, so this is acceptable.

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 three sentences, front-loaded with the core purpose question, and every sentence adds valuable rule information. It avoids fluff and redundantly stating the tool name. The structure flows logically from 'what does it do' to 'key rules' to 'error behavior,' making it highly scannable for an agent.

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?

Given the tool's complexity (7 params, nested objects, output schema), the description sufficiently covers the core legality rules and error conditions that an agent needs to know. The existence of an output schema removes the need to describe return values. It doesn't explain all generic protocol parameters, but those are likely common across tools. The description is complete enough for correct use of the main functional parameters (conditions, spent_since_turn_start).

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?

The schema has 7 parameters but only 14% have descriptions. The description partially compensates by explaining that the conditions parameter expects condition names and that unknown/non-condition names are refused. It also aligns with spent_since_turn_start by explaining refresh timing. However, it does not explicitly map to parameters like table_policy, asserted_facts, or policy_context, and it doesn't clarify whether conditions is required or how multiple conditions are handled. The compensation is incomplete given the low schema coverage.

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 opens with the question 'Is taking a Reaction legal right now?' which directly conveys the tool's purpose: to determine reaction availability. It specifies the resource (Reaction) and adds scope by clarifying refresh timing at the start of one's own turn, distinguishing it from generic availability checks. However, it doesn't use a conventional 'verb + resource' structure or explicitly name sibling alternatives, so it falls short of a 5.

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 question format implies the tool should be used when an agent needs to verify if a Reaction can be taken, and the rule details provide context for when it is relevant (e.g., during a character's turn or when conditions are involved). However, there is no explicit guidance on when not to use it, no mention of alternatives like opportunity_attack_provoked, and no exclusions. The usage context is implied rather than clearly stated.

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