Compare build options side by side

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

Annotations only declare readOnlyHint=true, so the description must carry the rest; it discloses the return contents (damage, kill times, survival, life/ES, resistances, attribute shortfalls, per-variant verdicts, delta vs first variant, best-for categories) and the platform constraint ('Windows only for now'). No output schema exists, and these disclosures fill that gap well, though depth/limits of each metric are not detailed.

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?

Front-loaded with the core action and constraint, then examples, then return summary, then platform note. Four sentences with little waste, though the examples sentence is dense and slightly long.

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 a very deep nested schema and no output schema, the description covers the essentials: what to pass (2–4 full-build variants with labels), what differing fields typically are, what comes back, and the OS limitation. An agent can call it correctly without opening the schema, though edge behavior (e.g. what if variants share no fields) is unstated.

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 single parameter is a variants array whose structure the description explains: each variant is a full build, carries a label, and variants 'usually share most fields and differ in weapons, items, passives, skills or ascendancy'. It also delegates field detail to evaluate_build, which is a useful pointer given the deep nested schema.

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?

Specific verb (calculate and compare), specific resource (2–4 build variants), and explicit differentiation from the sibling evaluate_build by stating variants use 'the same fields as evaluate_build'. The three concrete examples (two-handed vs one-handed, two ascendancies, with/without a unique) make the tool's identity unmistakable.

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 clear contexts for use via examples and the 2–4 variant constraint, and implicitly routes agents to evaluate_build for single builds. It stops short of an explicit 'when not to use this' or naming which conditions favor it over siblings like optimize_build or check_build, so not a full 5.

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