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 known. The description adds meaningful process context beyond that: a required preview step, owner approval, and requestId reuse for confirmation and recovery. It still leaves gaps around irreversibility (does delete archive or permanently remove?) and whether billing/spend history is affected.

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 action, which is good. But the telegraphic style produces ambiguous fragments ('Claim live only when status is active') and a trailing 'Fields: soclo://tools/...' reference of unclear value, reducing clarity rather than increasing it.

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 operation with no output schema and incomplete schema coverage, this is only partially complete. The confirmation workflow is covered, but the description omits what actually happens to the campaign and its history, whether the operation is reversible, and how outcomes should be recovered beyond reusing requestId.

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 only 43% across 7 parameters, so the description should compensate more. It clarifies confirm and requestId semantics (owner-approved confirm:true, same requestId on retry), but says nothing about accountId, adAccountId, platform, payload, or parameters.campaignId. Partial compensation only.

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 campaign', which clearly signals a destructive campaign operation in the Soclo Ads namespace. It does not explicitly distinguish itself from adjacent siblings like soclo_ads_update_ad_campaign_status or soclo_ads_bulk_update_ad_campaign_status, which an agent might consider as less destructive alternatives.

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 prescribes a workflow: preview first, then owner-approved confirm:true with the same requestId. However, it does not name alternatives (e.g., pausing via status update) or state when deletion is appropriate versus when it should be avoided, and 'Claim live only when status is active' is too cryptic to guide tool selection.

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