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

Annotations indicate readOnlyHint: false, destructiveHint: false, idempotentHint: false, which means the agent knows this is not read-only, not destructive in a dangerous way, and not idempotent. The description adds the bulk support detail (customer_ids) and the requirement for ad_group_id + criterion_id, which is useful. It does not mention failure modes or partial_failure behavior, but annotations already signal mutability. Since annotations are present and description adds some context, a 3 is fair.

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 concise: two sentences. The first gives the main action and required fields, the second adds bulk support. It is front-loaded and avoids fluff. Not a 5 because it could be slightly more structured (e.g., a note about partial_failure), but overall it is efficient.

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 tool has 6 parameters, no output schema, and annotations are minimal. The description explains the core functionality but doesn't cover all parameters (account, customer_id, partial_failure) or any return behavior. For a mutation tool with no output schema, it provides enough to invoke it correctly for basic use, but lacks detail on edge cases. It is adequate but not complete, so a 3.

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%, so the description must compensate. It explains that 'keywords' array needs ad_group_id and criterion_id, which helps understand the required fields. It also mentions customer_ids for bulk. However, it does not explain the 'account', 'customer_id', or 'partial_failure' parameters. With 6 params and only partial explanation, the description adds some value but not complete. Baseline for low coverage would be lower, but the description covers the two most critical aspects, so 3.

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 tool's purpose: 'Pause, enable or remove keywords.' It specifies the resource (keywords) and the actions (pause, enable, remove), which distinguishes it from sibling tools like google_ads_keyword_add (add) and google_ads_keyword_update_bid (update bid). It doesn't explicitly contrast with siblings, but the verb+resource is specific enough for a 4.

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 says 'Each entry needs ad_group_id + criterion_id' and mentions 'Bulk support: accepts customer_ids for batched execution.' This gives basic usage context but does not explicitly state when to use this tool vs alternatives (e.g., when to use google_ads_keyword_add vs this one). It implies you use it for status changes but lacks exclusions or alternative guidance, so a 3 is appropriate.

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