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

Annotations already flag destructiveHint=true, idempotentHint=false and openWorldHint=true; the description goes beyond them by disclosing the two-step spending/deletion preview + owner approval gate, requestId reuse for confirmation/recovery, and the 'active' status requirement before claiming success. It stops short of saying what existing companies are destroyed or whether downstream campaign targeting is recalculated.

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?

Very short and front-loaded: purpose first, then the approval workflow, then status semantics. The trailing 'Fields: soclo://...' reference is a cryptic token that costs a sentence without conveying information inline.

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, non-idempotent, 10-parameter nested mutation with no output schema, the description covers the safety flow but omits the consequences of replacement (existing list wiped, up-to-300k item limits) and gives no indication of what is returned or how to poll operation status.

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 only 60%, and the description does not compensate: it repeats the confirm/requestId semantics already described in the schema and defers the rest to an opaque pointer ('Fields: soclo://tools/...'). The undocumented parameters — accountId vs adAccountId, parameters.audienceId, platform, and the payload.companies item shape — receive no explanation in the description.

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 ('Replace audience companies'), which is distinguishable from update_ad_audience or add_users_to_ad_audience by the 'replace' semantics. However, it never clarifies that this replaces the entire company list on an existing audience (vs. appending), so the distinction from add_users_to_ad_audience still requires inference.

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?

Provides real procedural guidance for the write path: preview first, then owner-approved confirm:true with the same requestId, and only treat as live when status is active. That is workflow guidance rather than selection guidance — no sibling is named and there is no statement of when to prefer this over soclo_ads_update_ad_audience or soclo_ads_add_users_to_ad_audience.

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