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

Annotations already flag destructive, idempotent and openWorld, so the description isn't carrying the safety profile alone. It still adds genuine context the annotations don't: the owner-approval preview gate, confirm:true semantics, and requestId reuse for confirmation and outcome recovery.

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 front-loads the highest-stakes rule (preview then confirm), which is good. The trailing "Fields: soclo://tools/soclo_ads_update_ad_set" fragment is cryptic filler that tells an agent nothing it can act on.

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 10-parameter destructive mutation with deep nested objects and no output schema, the description covers the approval loop but not the updatable surface or what a successful update returns. It is adequate to avoid misuse on spending, but not complete for the tool's complexity.

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 60% and the confirm, requestId, adAccountId and expected* parameters already carry their own schema descriptions. The description gestures at confirm and requestId but adds no detail on budget, status, bidStrategy or the nested platformSpecificData, so the 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?

"Update an ad set" names the verb and resource, which is clear enough on its own. But it does not distinguish this tool from close siblings like soclo_ads_update_ad_set_status or soclo_ads_update_ad, and the closing "Fields: soclo://tools/..." pointer is a reference rather than a statement of what can be changed.

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 real workflow rule — preview spending/deletion first, then confirm with the same requestId, and only claim live when status is active. What it omits is when to pick this tool over the status-only sibling, or what a caller should do if only non-monetary fields change.

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