Add contacts to a customer list (consent required)

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

Annotations only state readOnlyHint=false and openWorldHint=true; the description adds real behavioral context by flagging that nothing is executed without confirm: true and that there is no server-side dry run, so the preview is client-side only. It stops short of saying what happens on partial failures or whether duplicates are merged.

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 short sentences with the operation stated first and the write gate second, so the critical safety fact is easy to spot. The stacked parentheticals (title repeated, then endpoint, then WRITE warning) make it slightly denser than necessary.

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 write tool with a nested body, no output schema, and a 4-parameter surface, the description covers the safety model but leaves the operational picture thin: no row format, no batching limit, no idempotency behavior, and no description of what the preview response contains.

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 schema description coverage at 50%, confirm and idempotencyKey are already documented in the schema, so the description only reinforces the confirm gate. It adds nothing about the 'id' parameter being the audience/list identifier, the per-row email/phone shape, defaultCountryCode, or the maxItems constraint on rows.

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 and resource ('Add contacts to a customer list') plus the underlying endpoint POST /v1/audiences/{id}/members. It is clearly distinguishable from audiences_removeMembers and audiences_sync by the 'add' verb, though it never names those siblings explicitly.

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 consent requirement and the confirm: true gate imply when the tool is usable and what must be done before calling, which is useful guidance. However, there is no explicit statement of when to prefer this over siblings (e.g., sync vs addMembers), no prerequisites about the list existing, and no mention of the 50,000-row batch ceiling.

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