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

Annotations already declare destructiveHint=true, idempotentHint=false, and readOnlyHint=false, so the safety profile is covered. The description still adds real behavioral context beyond that: a new private network is created by default unless private_network_id is supplied, and the tool is gated on organisation-level Scaleway enablement. It does not mention provisioning time, async behavior, or cost implications of the created infrastructure.

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 action and prerequisites, followed by defaults, discovery hints, and eligibility. Every sentence carries information, though the gateway default ('VPC-GW-S') slightly duplicates the gateway_type schema field and the length is on the high side for a description.

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 17-parameter creation tool with no output schema and only coarse annotations, the description covers prerequisites, credential lookup, private-network behavior, instance-type discovery, and eligibility. The notable remaining gap is what a successful call returns (cluster identifier) and whether provisioning is synchronous, which matters for a destructive, non-idempotent create.

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 100%, so the baseline is 3, but the description adds value the schema does not fully convey: default public gateway type 'VPC-GW-S', example instance sizes ('DEV1-M', 'GP1-S'), the create-vs-attach semantics of private_network_id, and which sibling tool supplies credential IDs. It does not restate the enum/range constraints that the schema already documents.

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?

States a specific verb and resource ('Create and provision a new self-hosted Kubernetes cluster on Scaleway Instances') and explicitly scopes it against the managed alternative ('Kapsule (managed) creation remains available in the portal and CLI'). An agent can distinguish it from create_aws_cluster, create_managed_cluster, and create_ankracloud_cluster without opening any 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?

Gives strong prerequisite and discovery guidance: 'Requires a Scaleway credential, SSH key credential, region, and zone', plus pointers to list_provider_credentials and list_instance_types with provider='scaleway' for valid values. Also states an eligibility precondition ('Only available to organisations with Scaleway enabled'). It lacks an explicit when-not-to-use statement relative to the other create_*_cluster siblings, so it falls just short of 5.

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