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

Adds substantial context beyond the annotations: server-side hashing means only hashed values are sent; invalid members are silently skipped so callers must diff the response against the input or the person stays in the list; sends occur in batches of 2000 and requestId only means 'accepted' (async semantics). These are critical behavioral facts not derivable from the destructiveHint/openWorldHint annotations.

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?

Purpose is front-loaded and the structure is logical (behavior then per-parameter notes). It is on the longer side and the inherited identifier rules reference another tool rather than restating them, which is efficient but adds a hop; a bit of trimming is possible.

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?

An output schema exists so return values needn't be explained, and the description covers normalization, silent skips, batching, and async acceptance — everything an agent needs to call and interpret this destructive operation correctly.

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 0%, so the description must carry the burden, and it does: audience_id (list ID or resource name), members (dicts with email/phone/address and nested address fields), validate_only as dry-run, and workspace optional for single-workspace accounts. This fully compensates for the empty schema descriptions.

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: removing members from a Customer Match user list via the Data Manager API. It also explicitly contrasts with the upload sibling (ads_upload_customer_match_members) whose identifier rules it inherits, so an agent can distinguish it without opening schemas.

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 removal context and validate_only dry-run are clearly explained, and it points to the upload tool for identifier rules. It doesn't explicitly state when NOT to use it (e.g., full-list deletion vs. member removal) or name alternative approaches, keeping it just short of a 5.

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