Add or remove customer list records

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

The description adds meaningful behavior beyond the annotations: it states the account-changing side effect, the batch limit of 50,000 per call, and that identifiers must be hashed. These are operational facts the annotations don't convey. It doesn't discuss whether removals are reversible or how partial failures behave, which is notable since idempotentHint is false.

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?

Three short sentences: action first, side effect second, parameter and limit facts last. Almost every line carries information. The reference to create_customer_list for hashing is efficient, though the ordering could front-load the batch limit before the hashing note for faster scanning.

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?

The output schema exists, so return values needn't be covered. But for a destructive, non-idempotent mutation, the description leaves out permissions requirements, retry semantics, and the meaning of the hash_identifiers flag, which the 0% schema coverage leaves undocumented elsewhere.

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 description coverage is 0% across five parameters, so the description must carry the load. It explains the two key semantics well: operation accepts ADD or REMOVE and identifiers must be hashed. It leaves ad_account_id, customer_list_id, and especially hash_identifiers (a boolean defaulting to true) unexplained, so it partially compensates rather than fully.

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 opens with a specific verb pair and resource: 'Add to or remove users from a customer list.' This clearly separates it from the read (pinterest_ads_list_customer_lists) and creation (pinterest_ads_create_customer_list) siblings. It references create_customer_list only for hashing conventions rather than to route an agent between them, so it falls just short of full sibling differentiation.

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 when to use this tool (when manipulating the membership of an existing customer list) and notes that it 'changes the account.' However, it never states when NOT to use it, nor does it reference the dedicated creation or listing tools. An agent must infer that pinterest_ads_create_customer_list is the right choice for a new list rather than deducing it from the text.

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