set_class

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

Without annotations, the description carries the transparency burden. It discloses re-rooting the passive tree and returning stats, but does not explicitly confirm whether previous passives are cleared or if the action is reversible. The phrase 'from scratch' implies reset but is not entirely explicit.

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 with no fluff: first states purpose, second explains parameters with examples, third describes effect and return value. Every sentence adds value, and key 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?

Given the complexity (2 params, output schema exists), the description is adequately complete. It explains the effect on the passive tree and return (stats). The output schema handles further return details. It does not mention prerequisites like an active build, but that is implied by 'active build'.

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 compensates by explaining class_name and ascendancy with examples (e.g., 'Mercenary', 'Witchhunter'). This adds meaning beyond the schema's type-only definitions, though valid values and case sensitivity are omitted.

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 sets the active build's character class and optionally ascendancy, using specific verbs ('Set') and resources ('active build's character class'). It distinguishes from siblings like set_level and set_config by specifying it re-roots the passive tree, a unique action.

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 explains the tool re-roots the passive tree, implying use at build start before passive allocation. It says 'from scratch' indicating a reset, but does not explicitly contrast with alternatives or state when not to use it.

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