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

Annotations already declare readOnly, idempotent and non-destructive, so safety is covered; the description still adds real value by disclosing exactly what the response contains (current metric values for the window, per-condition pass/fail, placements a zone action would touch, the intended action) and that it works on unattached rules. "Changes nothing" largely restates readOnlyHint, and nothing is said about cost/rate limits of a live-metric evaluation.

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 that leads with "Dry run" and then lists the return payload. Dense but every clause carries information; the trailing "why it did / didn't fire" is slightly redundant with the earlier per-condition pass/fail phrasing.

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 two-parameter, no-output-schema read tool this is nearly sufficient: the response shape and the no-side-effect guarantee are spelled out. Gaps are minor: no mention of whether the rule must be unattached versus attached, no error conditions for an invalid rule/campaign pair, and no note on where campaign_id comes from.

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?

Only 50% schema coverage: id is documented, campaign_id is not. The description compensates partially by framing the call as "against one campaign" and tying the id to the rule's window, which clarifies each parameter's role, but it adds no format, ID-source, or constraint detail beyond that.

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 and resource ("Dry run of an auto rule against one campaign") plus scope ("right now"), and immediately enumerates the outputs (metric values, per-condition pass/fail, affected placements, would-be action). An agent can distinguish it from attach_auto_rule, get_auto_rule and list_auto_rule_runs without opening any 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 context: use it "before it is attached" to see whether a rule would fire and why. That is a genuine when-to-use statement, but it never names the alternative tools (attach_auto_rule, get_auto_rule, list_auto_rule_runs) or states an exclusion, so the routing is inferred rather than explicit.

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