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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds real context beyond them: deletion requires an owner-approved preview/confirm handshake and requestId reuse for outcome recovery. The only weak spot is the cryptic line "Claim live only when status is active," whose meaning is not resolvable from the definition.

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?

It is short and the confirm protocol is front-loaded, but the trailing "Fields: soclo://tools/soclo_ads_delete_ad_creative" is a dangling reference that conveys no actionable information, and "Spending/deletion: preview" compresses the workflow into near-telegraphic phrasing.

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 destructive, open-world deletion tool with six parameters, a nested object, and no output schema, the definition covers the approval workflow but leaves open whether deletion is permanent, what happens to dependent entities, and how to check the outcome afterward (a soclo_ads_operation_status sibling exists but is not referenced).

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 50%; confirm and requestId are already documented in the schema, and the description largely restates them (owner-approved confirm:true, same requestId). platform, accountId, and parameters.creativeId have no description in either place, so the description does not compensate for the gap. Baseline 3 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 verb and resource ("Delete a creative"), which separates it from the many sibling deletion tools at the resource level (delete_ad, delete_ad_video, delete_ad_campaign). It does not explicitly distinguish deleting a creative from deleting the parent ad or from archiving via update_ad_creative, so it stops short of full sibling differentiation.

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 implies usage through procedure: preview the spending/deletion first, then send confirm:true with the same requestId. That tells the agent the call is a two-phase operation, but it never states when to choose this tool over soclo_ads_delete_ad or soclo_ads_update_ad_creative, nor what conditions make a creative eligible for deletion.

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