Insights apply negatives

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

Annotations already declare destructiveHint=true, idempotentHint=false, and openWorldHint=true, so the description is not obligated to re-state the safety profile. It does add real value above that bar: the write is 'guarded' and 'audited', it is a single atomic batch, negatives are exact-match, and ads.rollback is the undo path. It does not explain what 'guarded' means mechanically (the confirm parameter) or what happens on a partial/aborted run.

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?

A single front-loaded sentence with zero filler: the find step, the criteria, the write, and the undo path all land in one pass. Nothing is repeated from the title or annotations.

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?

An output schema exists so return values need no explanation, and annotations cover the danger profile. However, for a destructive, non-idempotent bulk write, the description does not say how many terms qualify, whether a dry-run/review step exists, what confirm expects, or what scope (account vs campaign) the negatives land in — gaps that matter before firing an irreversible mutation.

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 carries full burden for four parameters. It only loosely gestures at min_waste_cost_micros via '(cost, no conversion)' and hints at confirm via 'guarded'; the days lookback window, the cost-threshold units (micros, default 5M), and the meaning/format of confirm are never explained. With no structured parameter docs, this leaves significant ambiguity.

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 concrete compound action: find wasted search terms (cost, no conversion) and add them as exact negative keywords in a single write. This is clearly distinguishable from the read-only insights.search_terms sibling by its mutating 'add negatives' half, though the description never names the sibling or the account/campaign level where negatives are attached.

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?

Usage is implied rather than stated: use this when you want to apply negatives in one guarded, audited write instead of doing it manually via ads.mutate. It points to ads.rollback for undo, which is useful, but gives no guidance on when NOT to use it, e.g. when you want to review candidates first via insights.search_terms.

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