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

Annotations already flag destructiveHint=true and openWorldHint=true, so the safety profile is covered. The description adds genuinely new behavioral context: removal widens reach (the business consequence) and the operation requires explicit in-chat user confirmation, which explains the purpose of the `confirm` parameter. It stops short of saying the deletion is irreversible or what happens on partial batch failure.

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?

Two sentences, zero waste, with the core operation front-loaded and the confirmation constraint placed after the lookup hint. The parenthetical adds routing value rather than noise.

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 destructive, 5-parameter mutation with no output schema, the description supplies the essentials: identifier source, affected level, consequence, and confirmation gate. Remaining gaps (reversibility, batching limits, error behavior) are meaningful but secondary.

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 only 40% (account and confirm are documented; ad_group_id, campaign_id and criterion_ids are not). The description partially compensates by explaining that campaign_id/ad_group_id select the level and that selection is by criterion ID, but it never mentions the 200-item cap or whether the level IDs are required alongside the criterion list.

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 (Remove), resource (negative keywords), scope (campaign- or ad-group-level) and identifier type (criterion ID). An agent can distinguish it from google_ads_add_negative_keywords and google_ads_negative_list without opening a schema.

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?

Gives clear when-to-use context by naming where the criterion IDs come from (google_ads_keywords or google_ads_campaign_targeting) and a mandatory prerequisite (user confirmation in chat). It does not address when NOT to use it, e.g. versus the generic google_ads_remove tool.

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