Add, update, remove, or reorder one targeting rule

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

Annotations supply only destructiveHint=true; the description carries the rest and does so meaningfully — update is a partial patch ('changes only the fields you pass'), conditionGroups is a full replace rather than a merge, and clearing a field is impossible here. That merge-vs-replace distinction is exactly the kind of behavioral detail annotations cannot convey. It stops short of permissions/auth or failure behavior, so not a 5.

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 dense paragraph, but front-loaded with the core purpose and then ordered by action, so it is scannable. Every clause carries a constraint or an alternative; little waste, though the action-specific clauses could be broken into a list for faster lookup.

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 tool with a rich nested schema and an output schema, the description covers the mutation semantics, per-action requirements, and the escape hatch to a sibling tool. Return values are rightly omitted since an output schema exists. Only permission/error behavior remains unstated.

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 coverage is 100%, so the baseline is 3, but the description adds cross-parameter conditionality the schema does not: which params are required per action, that ruleIds must contain every existing rule id exactly once in evaluation order, and that conditionGroups overwrites groups. This is real semantic value beyond the per-field descriptions.

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 ('Edit a single targeting rule') and immediately scopes it against the sibling that replaces everything ('instead of replacing them all with update_targeting'). An agent can distinguish this from update_targeting and get_targeting without opening either 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 explicit per-action routing: what each action value needs (rule, ruleId, ruleIds) and even when to fall back to a different tool (clearing rolloutPercentage or userSegmentId requires update_targeting). It also names get_targeting as the source of rule ids, so the agent knows the prerequisite call.

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