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

Annotations only assert destructiveHint=true/idempotentHint=false; the description goes well beyond them by disclosing irreversibility, that config/workloads/data are destroyed, that CSI-provisioned persistent volumes are deleted unless retention_policy keeps them, and that the operation is refused when the volume inventory is unreadable. The refusal behavior and the volume-listing shown to the user are exactly the kind of operational context annotations cannot carry.

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?

Front-loaded with the danger ('PERMANENTLY delete') and every sentence carries operational content, but it is one dense block with mild redundancy ('all destroyed' / 'cannot be undone' / repeated consent instructions) that bullet points would have tightened.

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 high-risk mutation with no output schema, it covers everything an agent needs: preconditions (user verification), guardrail mechanics, the secondary consent gate, and the retention-policy exception. Nothing required to call it safely is missing.

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 already 100%, so the baseline would be 3, but the description adds real meaning: confirm_name mismatch causes refusal, and accept_volume_data_loss governs an explicit second-pass consent flow whose refusal payload names the volumes. This is behavioral contract detail beyond the schema's field-level text.

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 ('PERMANENTLY delete/deprovision') on a scoped resource ('an Ankra-provisioned self-managed cluster') and enumerates exactly what is removed (every VM, cloud resource, platform entry). The scope qualifier distinguishes it from the many managed-cluster and mesh siblings, so an agent can identify it without opening the 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 procedural guidance: the confirm_name guardrail must be echoed exactly, the user must type/confirm the name first, and accept_volume_data_loss may only be set after explicit user consent to volume data loss. It does not, however, contrast delete against nearby alternatives such as stop_cluster or delete_cluster_mesh, so the when-not-to-use case is left implicit.

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