list_reference_builds

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

Discloses key behavioral traits: these builds are 'offline, deterministic', 'deliberately diverse set', and returns only summary data (VERIFIED DPS/EHP, archetype tags, lever) with 'deliberately nothing to copy'. This goes beyond typical list tools and compensates for lack of annotations.

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 with a clear first sentence stating the purpose, followed by details on usage and return values. It is slightly verbose but every sentence adds value; the front-loading is effective.

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 output schema exists, the description appropriately avoids detailing return structure but still mentions key fields. It covers purpose, usage, and parameter semantics adequately for a browse tool. It does not discuss pagination or errors, but these are minor gaps.

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?

With 0% schema description coverage, the description adds significant meaning for the 'query' parameter by listing acceptable filter categories (class, ascendancy, skill, element, etc.). The 'limit' parameter is not explicitly described, but its default value is given in the schema, and the description implies it controls result count.

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 browses 'engine-verified reference / CALIBRATION builds' and explains they are 'corpus — offline, deterministic'. It distinguishes from sibling tools by emphasizing these are not templates and should not be copied or recommended, contrasting with tools like get_build or get_meta_builds that might provide full builds.

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?

Explicitly states when to use ('to calibrate') and provides strong negative guidance: 'never copy, export, or recommend one wholesale when a user asks for a build'. It instructs to 'build to the USER's stated goal and use these to sanity-check it', giving clear context and exclusions.

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