create_alert_rule

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

Annotations only tell us readOnlyHint=false, destructiveHint=false, idempotentHint=false. The description adds the key non-obvious behavior: the call is non-committal ('PREVIEW ONLY'), shows before/after state, and requires explicit approval before confirm_action. That materially changes how an agent should sequence the call.

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?

The critical constraint (PREVIEW ONLY) and the commit path are front-loaded, and the long rule-type catalog is dense and information-bearing rather than filler. The parenthetical glosses are tight. It is appropriately sized for a tool with 15 enum values, with little waste.

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?

With no output schema, no nested objects, and low schema coverage, the description does the heavy lifting: it explains the preview return ('before and after'), the delivery model, and the confirmation step. Only the exact preview payload shape and permission requirements are left unspecified.

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 only 40%, and crucially the 'type' enum carries no per-value descriptions in the schema. The description compensates by defining all 15 rule types in prose, plus the dropBy range (3–50) and acceptable channels. It adds real meaning beyond the schema, though keywordScope/rivalScope are only listed without explanation.

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?

The description states a specific verb and resource ('turn on an alert rule and choose where it is delivered') and immediately clarifies the otherwise-confusing 'create' name by flagging it as PREVIEW ONLY. It also names the confirm_action sibling used to commit, so an agent can place it against list_alerts and delete_alert_rule without opening another 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?

It gives a clear workflow: this call previews, the user approves, then apply with confirm_action. That satisfies the when-to-use question and names the alternative. It does not explicitly state when NOT to reach for it (e.g., editing/removing existing rules), so it stops short of a full 5.

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