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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds meaningful behavioral context beyond annotations: what is excluded ('expected outputs are not included in summaries') and pagination semantics ('hasMore: true means more items exist'). This is valuable but not exhaustive; no contradiction exists.

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 with no filler, and the core purpose is front-loaded. Each sentence earns its place: the first defines the result scope, the second connects outputs to downstream tools, and the third explains pagination behavior with a clear recommendation. The structure is tight and scannable.

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 rich input schema, annotations, and presence of an output schema, the description covers the important non-obvious details: exclusions from summaries, relationship to update/delete tools, hasMore semantics, and pagination guidance. Nothing critical an agent needs to call this correctly is missing.

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%, with all six parameters documented, so the schema carries the parameter-semantics burden. The description adds minimal parameter-specific value, only mentioning that item IDs feed other operations and advising against excessive pagination. This meets the baseline 3 for well-covered schemas but does not exceed 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?

The description clearly states the verb, resource, and scope: 'List an evaluation set's items.' It adds a precise distinguishing detail—'file pairings only; expected outputs are not included in summaries'—which differentiates it from broader evaluation-set or run-related tools. The explicit mention of item IDs feeding update/delete tools further anchors its purpose.

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 gives actionable usage guidance: item IDs feed update_evaluation_item / delete_evaluation_item and subset runs, and it advises preferring narrowing filters over pagination. It does not explicitly contrast with list_evaluation_sets or add_evaluation_items, but the guidance is strong enough for an agent to know when and how to use this tool.

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