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

Annotations already declare destructiveHint=true and idempotentHint=true, so the mutation risk profile is partly covered. The description adds genuinely useful behavior beyond that: "(partial)" implies a merge for omitted fields, and "A sent conditions list replaces the stored one" discloses replace-vs-append semantics, which is exactly the kind of surprise that matters on a 14-parameter destructive update. However it is silent on whether other list fields (tags) also replace, on permissions, and on the effect on in-flight schedule runs.

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 short sentences, front-loaded with the action and scope, with no filler. Nothing is wasted, though the extreme brevity for a 14-parameter destructive tool means the terseness is partly under-specification rather than pure concision.

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, 14-parameter partial update with no output schema, the description leaves too much unstated: no mention of what is returned, no guidance on merge behavior for non-conditions fields, no note on permissions or on whether edits affect an active schedule. The rich schema does much of the parameter work, but the behavioral envelope of the tool is largely unexplained.

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 57%, and the schema itself carries detailed prose for the complex nested objects (ranking, schedule, action_params, conditions scopes and metrics). The description contributes exactly one semantic fact beyond the schema: that a supplied conditions array overwrites rather than merges. That is valuable but does not compensate for the remaining undocumented parameters such as run_every_minutes or on_success_pause_rule.

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?

"Edit an auto rule (partial)" gives a specific verb and resource, and the "(partial)" qualifier separates it from create_auto_rule and from a full-replace edit. It does not name or contrast with siblings like create_auto_rule, preview_auto_rule, or get_auto_rule, so the differentiation is inferable from the name rather than stated.

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?

There is no guidance on when to use this versus preview_auto_rule (to test before saving), create_auto_rule (new rules), or attach_auto_rule (binding to campaigns). The description gives no preconditions about which fields must be resent or whether the rule must exist and be paused. Only the conditions-replacement rule hints at usage.

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