Set Scaleway bucket lifecycle rules (full replace)

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

Annotations already provide destructiveHint=true and idempotentHint=true, but the description adds crucial context beyond annotations: it explains that rules with 'expiration' permanently DELETE matching objects (not just transition), that this is a full replace (not a merge), and that confirm=true is required even if no destructive rules are present. This goes well beyond the annotation surface and prevents major errors.

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?

At three sentences, the description is efficient and front-loaded with critical warnings. The first sentence states purpose, the second delivers the most important behavioral notes (full-replace, destruction, confirm requirement), and the third adds storage class context. It's slightly verbose for a 4-param tool but earns its space by preventing mistakes. Could be trimmed slightly without loss.

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 destructive nature, 4 parameters (3 required), schema coverage of 75%, and no output schema, the description provides complete guidance for correct usage. It covers full-replace semantics, destructive potential with explicit deletion warning, confirm requirement, storage class targets, and scope (Scaleway storage classes). The sibling set is large, but the description effectively isolates this tool from other S3 configuration tools. No gaps exist for safe invocation.

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 75%, covering 3 of 4 parameters. The description adds value by explaining the overall replace semantics and linking to schema fields like 'expiration_days'. However, it doesn't walk through each parameter individually. Since schema already documents 'rules', 'bucket', 'region', and 'confirm' reasonably well, the description compensates by contextualizing the rule structure (e.g., storage class options) and the mandatory confirm flag. A score of 4 reflects strong synergy with schema.

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 verb ('Set'), resource ('bucket's lifecycle rules'), and critical behavioral qualifiers ('FULL-REPLACE', 'DESTRUCTIVE'). It distinguishes this tool from siblings like 'scaleway_s3_get_bucket_lifecycle' (read) and 'scaleway_s3_delete_bucket_lifecycle' (remove all rules), which are the only other lifecycle-related tools. The description explicitly flags the destructive nature and full-replace semantics, making the purpose 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 provides explicit guidance on when to use this tool vs alternatives. It notes that rules with expiration are destructive and require 'confirm=true regardless of rule content'. It also specifies that rules apply to Scaleway storage classes and transitions target specific classes (ONEZONE_IA, GLACIER), helping the agent avoid misuse. The sibling list includes complementary tools like get/delete lifecycle, making the boundary clear.

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