resolve_improvised_stunt

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

With no annotations provided, the description carries the full burden. It effectively describes the tool's behavior: it resolves improvised actions with skill checks, damage, and consequences based on provided guidelines. It includes DC and damage scales, and an example showing the expected input structure. However, it lacks details on error handling, side effects, or system state changes beyond the example.

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: it starts with the core purpose, provides context and guidelines, and ends with a comprehensive example. Every sentence adds value, but it is moderately long due to the detailed guidelines and example. It could be more front-loaded by emphasizing the example's role earlier.

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 (13 parameters, nested objects, no output schema, no annotations), the description does a good job. It explains the tool's role, provides scaling guidelines, and shows a full example. However, it doesn't cover all parameter nuances or potential outputs, leaving some gaps for a tool of this complexity.

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 very low (8%), so the description must compensate. It adds significant meaning: the example illustrates how parameters like 'narrative_intent,' 'skill_check,' and 'consequences' should be used, and the DC/damage guidelines inform 'dc' and 'success_damage' values. This goes beyond the bare schema, though it doesn't cover all 13 parameters explicitly.

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 clearly states the tool's purpose: 'Resolve a creative player action using the Rule of Cool.' It provides specific examples ('kick the brazier of coals into the zombie horde,' 'swing from the chandelier and kick both guards') and distinguishes it from sibling tools by focusing on improvised stunts rather than standard combat actions or narrative notes.

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 implicitly defines when to use this tool: for creative, improvised player actions that require mechanical resolution. It provides DC and damage guidelines to help assess appropriateness. However, it does not explicitly state when NOT to use it or name specific alternatives among the many sibling tools, though the context suggests it's for non-standard actions.

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