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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, so the safety profile is structured. The description adds genuinely new behavior: a two-phase preview/owner-approval flow, the requestId reuse pattern for confirmation and outcome recovery, and the "claim live only when status is active" condition. The phrasing is terse and the status quote is cryptic, keeping it from a 5.

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 confirmation requirement is front-loaded, but the delivery is telegraphic ("Spending/deletion: preview, then owner-approved confirm:true") and the trailing "Fields: soclo://tools/..." pointer is an unresolved reference that consumes space without clarifying anything.

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, 6-parameter mutation with no output schema, the description covers the approval gate reasonably well. It still omits what removal affects (is the asset detached from the ad set, deleted from the account, both) and never points at soclo_ads_operation_status for the status check it alludes to, leaving the agent to infer post-call behavior.

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 coverage sits at 50%, and the only parameters the description touches (confirm, requestId) are already documented verbatim in the schema. The three required nested fields — adSetId, assetResourceNames, adGroupAssetResourceNames — get no explanation in either place, and the description does not compensate for that gap.

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+resource ("Remove ad-group assets") that matches the name and title, so an agent immediately knows the operation. However, it does nothing to distinguish itself from close siblings like soclo_ads_attach_ad_group_assets or soclo_ads_update_ad_group_assets, which the agent must infer from the name alone.

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?

It gives a workflow (preview, then confirm:true with the same requestId) which tells the agent *how* to call it safely, but not *when* to prefer it over the sibling attach/update variants. The exclusions and alternatives are left implicit, which is a real gap in a family of ~200 similarly named ads tools.

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