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

Annotations already flag destructiveHint=true and openWorldHint, so safety is covered structurally. The description adds non-obvious semantics that annotations cannot express: signals 'guide Google' and do not restrict reach, and it 'runs directly' (executes immediately rather than staging a change). It stops short of saying what removing a signal destroys or whether it is reversible.

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 sentences, front-loaded with the action and scope, and the parenthetical references are compact. The dense stacking of references ('see google_ads_campaign_targeting / assets') is slightly noisy but each clause carries information an agent needs.

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 an 8-parameter destructive mutation with no output schema, the description covers the essentials: which action to pick, where IDs come from, how removal is keyed, and that reach is not restricted. Remaining gaps are permission requirements and the effect/reversibility of removal, which matter given destructiveHint=true.

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 only 25%, so the description has to compensate, and it does for the key parameters: it maps 'affinity/in-market IDs' to user_interest_ids and 'your audience lists' to user_list_ids, and explains signal_resource_name as the removal key. asset_group_id and the add/remove action are left to the schema, but those are largely self-evident from names and enum.

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+resource pair twice: add an audience signal (affinity/in-market IDs and/or customer lists) to a Performance Max asset group, or remove one by resource name. Scope is explicit ('Performance Max asset group'), which separates it from generic audience tools like google_ads_add_audiences, and the data source (google_ads_find_audiences) is named.

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?

Tells the agent where the inputs come from (google_ads_find_audiences for affinity/in-market IDs and audience lists) and how removal differs (by signal_resource_name), plus pointers to campaign_targeting/assets. It does not explicitly say when NOT to use it or name the alternative audience tool for non-PMax campaigns, so routing is implied rather than spelled out.

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