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

Annotations already declare destructiveHint, idempotentHint, and openWorldHint, so the safety profile is known. The description adds real value beyond that: the required confirm/requestId confirm flow and the 'claim live only when status is active' nuance about finalization. The phrase 'Claim live only when status is active' is somewhat cryptic but does convey delete finalization semantics.

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?

Front-loaded with the destructive action and confirm flow, but the trailing 'Fields: soclo://tools/...' pointer contributes little for an agent selecting/invoking the tool, and 'Claim live only when status is active' is under-explained filler that doesn't clearly earn its place.

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, nested-parameter tool with no output schema, the description covers the confirmation workflow adequately but omits how audienceId is obtained, what platform values are valid, or what status outcome signals success. It is minimally complete for invocation but leaves real gaps.

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?

With 50% schema coverage, the description should compensate, but it only echoes confirm and requestId behavior already documented in the schema descriptions. The required audienceId, platform, adAccountId, and accountId receive no explanation in the description, leaving half the parameters thinly specified.

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+resource ('Delete custom audience') matching the name, so an agent can locate it among the delete_* siblings. It does not explicitly contrast with update_ad_audience or explain what audience types are covered, but the core purpose is unambiguous.

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 implies the two-step flow ('preview, then owner-approved confirm:true with the same requestId'), which is genuinely useful sequencing guidance. However, it never states when to use this vs. siblings like update_ad_audience, nor what warrants a preview, leaving usage context implied.

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