simulate_fight

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the return values (expected winner, DPS, crit chance with opponent's Tenacity, time-to-kill), names the optional reduce_a/reduce_b inputs, points to the math reference, and clearly states model limitations. It does not explicitly say the simulation is deterministic or side-effect-free, but 'simulate' plus the detailed scope conveys the expected behavior well.

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 tightly written sentences with no fluff. The first sentence states the core action and scope, the second lists the return values, and the third clarifies optional parameters and limitations. Every sentence earns its place and the most important information is 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 complex tool with 11 parameters, no output schema, and no annotations, the description provides a solid overview of outputs and limitations, but it omits parameter-level guidance for the majority of inputs. An agent could still be uncertain about how evo, level, stars, and talent fields combine to form a build, or what 'damage-reduce ratings' mean exactly. The return list is helpful but not enough to fully compensate for the lack of schema descriptions.

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 0%, so the description must compensate for 11 parameters, but it only explains reduce_a/reduce_b. The hero_a/hero_b parameters are inferable from their names, but evo, level, stars, talent_a, talent_b, talent_a_lvl, and talent_b_lvl receive no semantic explanation in either the schema or the description. This leaves significant room for misunderstanding how these parameters shape a 'hero build.'

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 uses a specific verb ('Simulate') and resource ('1v1 auto-attack duel between two hero builds'), and clearly distinguishes it from skill-related sibling tools by stating that skills, energy, heals, shields, and crowd control are not modeled. It also names the verification source and the expected outputs, leaving no ambiguity about what the tool does.

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 communicates the intended use case: an auto-attack, damage-formula-based duel between two hero builds. It also states explicit exclusions ('Skills, energy, heals, shields and crowd control are not yet modeled'), which tells the agent when not to use it. However, it does not name specific sibling tools or provide explicit alternative routing, such as 'use combat_effects for full combat logic.'

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