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

Annotations already flag destructiveHint=true and openWorldHint=true, so the description usefully spends its budget on what the annotated destructiveness actually entails: a spending/deletion action requiring a preview plus owner-approved confirm:true keyed to the same requestId. It also implies the operation is not live until a status is active. That is real value beyond the structured fields, though the "claim live" sentence stays opaque.

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, but several fragments fail to earn their place: the first sentence merely repeats the title, "Claim live only when status is active" is unparseable in isolation, and "Fields: soclo://tools/soclo_ads_send_conversions" is a dangling resource pointer with no instruction on when or why to follow 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, non-idempotent tool with 10 parameters, a deeply nested events/user/items payload, and no output schema, this description is far too thin. It omits the required preview tool, the meaning of destinationId/platform, and consent handling, and never mentions what a successful send returns or how to recover an outcome.

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%, so the schema already documents most parameters, and the schema itself defines confirm, requestId, adAccountId, and the expected* preview validators. The description only reinforces the confirm/requestId pairing and adds no syntax or semantics for the large payload, events, consent, destinationId, or platform fields.

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 supplies a clear verb and resource ("Send conversion events"), but the opening sentence is a verbatim restatement of the title with no additional clarifying scope. It does nothing to distinguish this tool from close siblings like soclo_ads_adjust_conversions, soclo_ads_create_conversion_action, or soclo_ads_get_conversions_quality, leaving the agent to infer which one fires real conversion data.

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?

There is genuine procedural guidance — "preview, then owner-approved confirm:true with the same requestId" — which implies a precondition workflow. However, it never names the sibling preview/quote tool the agent should call first, and "Claim live only when status is active" is cryptic enough to be unactionable without prior context.

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