Compare AI models on published benchmark results

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

Annotations already declare readOnly, idempotent, non-destructive, openWorld, so the safety profile is covered. The description adds genuinely non-derivable behavior: no new aggregate score is computed, and benchmarks with comparable_across_labs=false reflect a single lab and should not drive a decision. That data-quality caveat is the kind of context annotations cannot express.

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, then usage routing, then the data-quality caveat, in three tight sentences with no filler. Slightly dense with parenthetical field lists, but every clause carries information.

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?

An output schema exists so return values need no explanation. Scope, the 'no aggregate computed' limit, the routing condition, and the comparable_across_labs caveat together give an agent everything needed to call and interpret this correctly; openness is covered by openWorldHint.

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 100% and both parameters are documented there, so the baseline is 3. The description does clarify the intent of the optional profession parameter (include the models' rows in its ranking) and implies the minItems=2 constraint, but adds no syntax, format, or resolution guidance beyond the 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?

States a specific verb and resource ('put two or more frontier models side by side on the benchmark results') and enumerates what is surfaced per benchmark (score, unit, source table, evidence grade). It also names the sibling it is not (recommend_model_for_profession), so an agent can distinguish it without opening either schema.

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?

Explicit trigger ('use this when the user is choosing between specific models') and an explicit exclusion with the alternative tool named for the opposite case (user has not named any models). Nothing about routing is left to inference.

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