Create a lookalike of a synced customer list on an ad account (Action)

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

Annotations only say readOnlyHint=false and openWorldHint=true; the description adds genuinely new context by flagging the tool as a WRITE, stating that nothing is sent unless confirm: true, and noting there is no server-side dry run. What is still missing is the blast radius (new audience created on the ad account) and any rate-limit or async-processing behavior.

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?

Two compact sentences with the write-safety caveat front-loaded into the second sentence; nothing is padded. It does largely restate the title verbatim, which costs a little value but no clarity.

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 creation tool with a nested required body of five undocumented fields and no output schema, the description leaves a lot unstated — what the returned preview looks like, what constraints apply to ratio, and how idempotency behaves on retry. The write-gating note is helpful, but the parameter surface remains opaque.

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 67% but only for the top-level confirm and idempotencyKey, both of which already have schema descriptions. The nested body's five required fields (name, adAccountId, sourceAudienceId, countries, ratio) carry no descriptions in either the schema or the description, and the description never explains the ratio range, country-code format, or what sourceAudienceId must reference.

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 gives a specific verb, resource, and scope ("Create a lookalike of a synced customer list on an ad account") plus the HTTP endpoint, which clearly separates it from audiences_createList or audiences_addMembers. It stops short of explicitly naming a sibling, but the distinctive "lookalike" resource makes the intent 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 confirm: true requirement makes the invocation contract concrete, but there is no guidance on when to choose this over audiences_createList or when a source audience must first be synced. Prerequisites (source audience existence/sync state) and exclusions are left to inference.

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