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

Annotations already declare destructiveHint=true and idempotentHint=true, and the description adds genuinely new context: the two-phase owner-approval gate, the requestId correlation requirement, and the rule not to claim liveness until status is active. It leaves unstated what the removal does to the user's existing permissions or whether it is reversible.

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?

The destructive-approval constraint is front-loaded and the workflow is packed into two compact clauses with no padding. The trailing 'Fields: soclo://tools/...' pointer is a token of dubious value but does not disrupt structure.

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, six-parameter mutation with a nested object and no output schema, the description covers the approval protocol but omits the accountId vs adAccountId distinction and any description of the return/status shape the agent should check. Adequate but with clear gaps an agent would hit on first use.

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 is 50%, and the description only elaborates on confirm and requestId, both of which already carry schema descriptions. It does not explain the relationship between the required accountId and the optional adAccountId, nor does it describe the nested userId or platform parameter, so it does not compensate for the coverage 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 names a specific verb and resource ('Remove a user from an ad account'), matching the tool name precisely. It does not explicitly differentiate from the close siblings soclo_ads_assign_ad_account_user and soclo_ads_remove_page_user, but the verb+resource pairing is unambiguous enough for selection.

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 lays out the required operating flow: preview first, then call again with confirm:true and the same requestId, and only claim success once status is active. This is concrete procedural guidance, though it does not name alternative tools or state what to do if the owner declines.

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