Add/remove audience users

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

Beyond the annotations, the description reveals the server-side SHA-256 hashing behavior, the exact condition for setting hashed=true, normalization rules for email and phone, the 2500-user batch limit, and a privacy instruction to never log raw lists. This substantially exceeds the annotation info and does not contradict readOnlyHint=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 compact sentences front-load the core operation and then stack only high-value operational constraints: hashing, hashed condition, batch limit, and logging caution. There is no filler or needless repetition of schema defaults.

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 mutating member-management tool with no output schema, the description covers the operation mapping, input format, hashing behavior, and batch limits, which are exactly what an agent needs to invoke it correctly. It omits return details and some niche identifier fields, but those do not prevent correct invocation.

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 only 20% schema description coverage, the description carries the load for the hardest decisions: raw vs hashed values, normalization rules, the Update/Delete meaning, and the batch cap. It does not explain less-common identifier variants like device_id/twitter_id/phone_number or the custom_audience_id source, but it makes the required users and hashed parameters actionable.

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?

Opens with a precise verb/resource pairing: 'Add (Update) or remove (Delete) members of a custom audience.' This clearly distinguishes the tool from sibling tools that create, update, or delete the audience object itself, and it maps the X Ads Update/Delete operation semantics to add/remove. No ambiguity remains.

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 first sentence provides clear context: this tool is for membership changes to an existing custom audience, so an agent can route add/remove requests here rather than to x_ads_create_audience or x_ads_delete_audience. It does not explicitly name alternatives or state exclusions, so it misses the top score, but the usage context is unambiguous.

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