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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful behavior beyond annotations: 'Results are paginated' and 'counts must not be summed across overlapping groups.' These disclose edge-case behavior and response traits that the agent needs to know.

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 concise at three sentences, front-loading the core purpose. However, the third sentence about 'Edition dimensions' is unclear and potentially confusing, though it is not redundant. The structure is efficient overall.

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 tool's complexity (6 top-level params, one required, a large nested filters object, no output schema), the description is far too thin. It does not explain the meaning of dimensions, how pagination works (page vs offset), what the response looks like, or how filters interact with grouping. The caveat about overlapping groups is helpful but leaves the agent guessing on essential details needed for correct invocation.

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 must compensate for missing parameter explanations, but it hardly does. It mentions 'up to two dimensions' (matching groupBy) and 'Edition dimensions' (a concept not even present in the enum values), but ignores page, offset, filters, pageSize, periodYears, and the complex filters object. The 'Edition dimensions' remark is cryptic and could mislead, as no enum value is called 'edition'.

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 states a specific action—'Group distinct works by up to two dimensions'—and identifies the resource (works in a catalog). It clearly distinguishes this from list/search operations by focusing on grouping and aggregation. The title 'Compare catalogue groups' is vaguer, but the description adds enough specificity to understand the core function.

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 implies usage when grouping works is needed, but it does not explicitly state when to choose this over siblings like count_catalog or list_works. There are no alternatives referenced, nor any conditions where this tool should not be used. The caveats about edition dimensions and pagination give partial usage context but no direct comparison with other tools.

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