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

Annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the description's job is to add behavioral context, which it does: results may contain llmContext guidance the agent must follow, and the list returns full set objects rather than summaries. This exceeds what annotations alone convey, though it does not disclose pagination behavior beyond the schema's nextPageToken.

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?

Three sentences, each carrying distinct information: the core action with scoping, the no-get-by-id disambiguation paired with return shape, and the llmContext instruction. The most decision-relevant facts are front-loaded and there is no padding.

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?

With 100% schema coverage, a complete safety annotation set, and an output schema present, the structured fields already carry most of the burden. The description rounds this out with the llmContext behavior disclosure and the scoping explanation. The only notable gap is the lack of explicit differentiation from list_evaluation_items, given the large sibling list.

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%, so the baseline is 3, but the description adds meaning on top: it maps entityId to concrete accepted value domains (extractor/classifier/splitter IDs) and justifies the pagination parameters by noting full set objects are returned. The description compensates where the schema is terse without duplicating it.

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 ('List evaluation sets') with an explicit scope qualifier ('optionally scoped to one extractor/classifier/splitter via entityId'). The 'evaluations group' parenthetical and the explicit note about the absence of a get-by-id tool distinguish it from the many get_* and list_* siblings without requiring schema inspection.

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?

Provides clear context for when to call it — enumerate evaluation sets, optionally filtered to one entity — and clarifies that there is no get-by-id alternative, so this list is the way to retrieve full set objects. It stops short of explicit when-not-to-use guidance or contrasting sibling tools such as list_evaluation_items, leaving some routing to inference.

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