Create a Scaleway Audit Trail custom alert rule

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

Annotations already indicate non-idempotent (`idempotentHint: false`) and non-destructive (`destructiveHint: false`) behavior. The description adds critical behavioral context beyond annotations: the tool requires write permissions beyond AuditTrailReadOnly with an explicit resolution path via `scaleway_iam_set_policy_rules`, it cannot modify the query in place, and it includes a frank caveat about a known API 501 error with instructions to not retry.

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 description is front-loaded with the core purpose and mechanism in the first sentence, then progressively covers behavioral constraints, permissions, and the important caveat. It is efficient but slightly verbose in the caveat section; a more concise version could separate the core from the live-verified note. Still, every sentence earns its place by providing actionable guidance.

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?

Given the tool's complexity (7 parameters, no output schema, multiple siblings in the audit family), the description is remarkably complete. It explains the rule logic, mutation constraints, required permissions (with resolution), and a known deployment limitation with clear alternative. No gaps remain that an agent would need to guess about.

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 description coverage is 100%, so the schema already documents all 7 parameters thoroughly. However, the description adds valuable semantic context: it explains the relationship between `occurrences` and `evaluation_window` (defining the triggering condition), it clarifies that the CEL query field surface is undocumented by Scaleway, and it notes the region default. This enriches the schema's bare definitions.

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 clearly states the tool creates a custom Audit Trail alert rule, specifying the exact mechanism (CEL expression evaluated against incoming audit events, firing when matching events exceed occurrences within evaluation_window). It also distinguishes this from the preconfigured alert rules tool (`scaleway_audit_list_alert_rules`), which is a sibling.

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?

The description explicitly states when to use this tool (to create a custom rule with a new query), provides an alternative (`scaleway_audit_update_custom_alert_rule` for metadata-only edits), clarifies when NOT to use it (changing the query requires creating a new rule and deleting the old one), mentions prerequisites (write permissions via `scaleway_iam_set_policy_rules`), and even includes a live-verified caveat about the 501 error with guidance to not retry and use the alternative `scaleway_audit_list_alert_rules` instead.

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