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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description adds a concrete retry rule, but omits whether deletion is permanent/recoverable and what happens if itemId is unknown – gaps that matter for a destructive operation.

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 short sentences, front-loaded with the action and scope, with the retry hint last. Nothing wasted.

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?

An output schema exists so return values needn't be explained, but for a destructive, 3-required-param tool with 0% schema descriptions the definition should at least state whether the deletion is irreversible and what the itemId refers to beyond 'the item the user selected'.

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 carry the load. It only clarifies idempotencyKey semantics; brandId and itemId are partially inferable from the prose ('the specific saved evidence item ... from this brand') but no format or failure semantics are given.

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+resource ('Delete the specific saved evidence item') and scopes it to a brand. This distinguishes it reasonably from delete_intelligence_target and delete_saved_ad, though it never names those siblings explicitly.

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 only guidance is retry behavior ('Reuse idempotencyKey on retry'), which is lifecycle advice rather than selection advice. There is no statement of when to use this instead of delete_intelligence_target or delete_saved_ad, nor any precondition or exclusion.

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