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

Annotations already mark destructiveHint=true, and the description adds valuable behavioral context: the deletion is permanent, cannot be undone, and does not affect past run metrics. This goes beyond the annotation flags without contradicting them.

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 concise sentences with no filler: the first states the action and resource, the second states permanence and non-impact on past runs. Important caveats are front-loaded.

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 delete operation with a full input schema, output schema, and annotations covering destructive intent, the description covers the essential behavioral facts. Nothing an agent needs to call it 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 clear descriptions for all four parameters including ID formats and environment constraints. The tool description itself adds no parameter-specific guidance, so the baseline score 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 action (permanently remove), a precise resource (one ground-truth item from an evaluation set), and the scope of the effect. This clearly distinguishes it from sibling tools like update_evaluation_item or add_evaluation_items.

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 operation is unambiguous: use this when a specific evaluation item must be permanently removed. It doesn't explicitly name alternatives, but the resource and action are specific enough that an agent can determine when it is appropriate.

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