List Scaleway Audit Trail export jobs

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

The annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, so the agent knows this is a safe, non-destructive read operation. The description adds useful context about the behavior: the pagination cap (max_pages), the potential for a 'truncated' indication, and the fact that it filters by Organization scope (not user/workspace). However, it doesn't describe the output format or any edge cases (e.g., when no export jobs exist). With the annotations covering the core safety traits, a 3 is appropriate.

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 three sentences: the first clearly states the tool's purpose, the second connects it to the console UI, and the third provides crucial authorization guidance. It's nearly concise and well-structured, though the third sentence is a bit dense and could be slightly tighter. Still, every sentence adds value with minimal 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?

Given the tool has 4 parameters with 100% schema coverage, annotations covering safety, and no output schema, the description provides a decent picture. It covers the core purpose, scope (Organization-level), key return fields, and a critical authorization edge case. However, it lacks a description of the return format or how to interpret the response (e.g., what 'last run' and 'last status' look like). For a listing tool, this is still reasonably complete, but not exhaustive.

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?

The schema description coverage is 100%, meaning each parameter is already documented in the input schema. The description adds some contextual value by explaining the 'max_pages' parameter's safety cap and the 'truncated' response field, but it doesn't elaborate on the 'name' filter's exact match requirement beyond what's in the schema. Overall, the description adds marginal value on top of an already well-documented schema, earning a 4.

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 it lists the Organization's Audit Trail export jobs, specifies the purpose (shipping audit events to Object Storage), and includes details like S3 destination config, last run, and last status. It also distinguishes this tool from other audit tools like query tools and from the other export job tools (create, delete), making its purpose distinct and unambiguous.

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 it (viewing the Organization's export jobs, like the console's Audit Trail > Exports page) and crucially provides an exclusion scenario: it notes that a read-only credential (AuditTrailReadOnly) may not be sufficient, and if the call fails with permissions_denied, to grant the write permission set. This is excellent guidance, preventing authorization confusion and directing the agent to a specific sibling tool (scaleway_iam_set_policy_rules) for remediation.

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