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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the safety profile is partly covered. The description adds a genuine behavioral trait beyond that: criteria have no paused state, so this removes them outright rather than disabling them. It stops short of describing permission requirements or what happens if the criterion no longer exists.

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, front-loaded with the action, then a clarifying constraint. The example and the no-paused-state note both earn their place by preventing a mistaken pause-then-remove attempt; there is no filler.

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 mutation with no output schema, the description covers what it removes, the source tools, and the permanence nuance, while the schema richly documents parameters including the validateOnly dry run. Missing only edge-case behavior (criterion already gone, permission needs), which is minor given annotation and schema coverage.

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 description says nothing about any of the 5 parameters. Schema description coverage is 80% (criterionId, customerId, extraFields, validateOnly are all documented in-schema), so the schema carries the load and the baseline of 3 applies. No extra syntax or format guidance is added beyond what the schema provides.

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 (undo/remove a campaign-level criterion) and enumerates exactly which criterion kinds it covers (location, device exclusion, ad schedule block, negative keyword). Naming set_campaign_targeting and add_negative_keywords as the creators lets an agent distinguish this from the sibling add/get tools 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?

Explicitly states when to reach for it — undoing a criterion created by set_campaign_targeting or add_negative_keywords — and gives a concrete trigger example ('actually don't exclude mobile after all'). It also explains that criteria lack a paused state, so removal is the only disable path, which resolves the obvious alternative (why not just pause it?).

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