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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds real value beyond them by disclosing what is returned (test scores, rank, memory needs) and the cardinality bound of 2-6 models, which matters since there is no output schema.

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?

Two tight sentences with zero waste: usage trigger first, return contents second. Nothing redundant or padded.

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 one-parameter read-only tool with no output schema, the description covers when to use it and what comes back, which is enough to invoke it correctly. Only the omission of sibling routing (vs. get_model/find_models) keeps it from fully complete.

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 the single param is simply an array of model names/slugs. The description's '2 to 6 models' merely restates the schema's minItems/maxItems, adding no new format or naming guidance beyond the schema. Baseline 3 applies.

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 (compare open-weight models) plus the exact output content: test scores, rank, memory needs. The 'two or more' framing implicitly separates it from single-model siblings like get_model, but no sibling is named explicitly, so it falls short of a 5.

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 a clear trigger condition ('whenever the user asks how two or more open-weight models compare, or which of them to pick'), which also rules out single-model lookups. It never names the alternative tools (get_model, find_models) or says when to prefer them over this one.

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