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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description's only addition is retry guidance for the idempotency key, which restates the idempotent hint in operational terms; it says nothing about whether deletion is reversible or what confirmation semantics apply.

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 with the operation front-loaded and no filler. It is efficient, though the second sentence is a behavioral note rather than usage context, and the whole definition is arguably under-specified for a destructive tool.

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 described, and annotations cover the destructive/idempotent profile. However, for a required-parameter destructive delete with zero schema coverage, the description omits any hint of how to obtain a valid itemId/brandId or the consequences of a wrong id, leaving it only minimally complete.

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% across all three required parameters, so the description carries the full burden. It only touches idempotencyKey (reuse on retry) and gives no meaning to itemId or brandId beyond their names, leaving the agent to infer that itemId must be a previously listed saved item scoped to brandId.

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 verb and resource ('Delete the specific saved evidence item') and scopes it to a brand, which separates it from sibling deletes like delete_saved_ad and delete_intelligence_target. It is clear enough to identify the operation, though it never uses the resource name 'intelligence saved item' the agent will see in sibling tools like list_intelligence_saved.

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 'Reuse idempotencyKey on retry.' There is no statement of when to choose this tool over delete_intelligence_target or delete_saved_ad, no precondition such as item ownership or prior listing, and no warning about when deletion is inappropriate.

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