google_ads_location_targeting_update

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

Without annotations, the description carries full weight and provides extensive behavioral details: it states the tool is mutating, clarifies that adds create new criteria and removes delete them by criterion_id, explains reversibility via inverse operations, notes the return format, and describes auto-prefixing of bare IDs. There are no contradictions.

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?

The description is compact, with every sentence providing essential information. It front-loads the main purpose and packs critical usage details (reversibility, auto-prefixing, ordering) without redundancy.

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?

Given there is no output schema, the description fully covers the return format ('Returns [{resource_name}]'). It also addresses prerequisites (customer_id fallback, campaign_id source) and the full operational behavior, making it self-sufficient for 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?

The input schema already provides 100% coverage for parameters, but the description adds meaningful context: explains the order of operations (adds first, then removes), details the auto-prefixing behavior for bare IDs, and specifies that remove_criterion_ids come from the list tool. This adds value beyond the schema.

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 clearly states the action: 'Add and/or remove location criteria on a Google Ads campaign in a single mutate.' It identifies the tool's specific verb ('add/remove'), resource ('location criteria'), and scope ('on a campaign'), effectively distinguishing it from sibling tools like google_ads_location_targeting_list.

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 explicitly says 'At least one of add_locations / remove_criterion_ids must be provided' and explains how to obtain IDs for additions and removals. While it doesn't contrast with alternative tools, the context implies this is the only tool for mutating location criteria, making usage clear.

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