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

Annotations already flag destructive=true and idempotent=false, but the description adds substantial context: a live pre-read of classes/volumes/claims, refusal messages naming each claim and volume, refusal on read failure ('Not checked'), and the fact that provisioned volumes are untouched. It also discloses the non-reversible nature and the kubernetes.write requirement.

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 most important constraint — refusing in-use classes — is front-loaded, and nearly every sentence carries distinct operational value. The UI/CLI escape hatch is slightly verbose but genuinely useful for a blocked agent.

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 destructive, non-idempotent tool with no output schema, the description covers refusal paths, side effects, reversibility, permission requirements, and alternatives. Nothing an agent needs to call it safely and correctly 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 100% for both parameters, so name and cluster_id are already documented in the schema. The description adds no syntax or format detail beyond that — the baseline 3 reflects schema doing the heavy lifting.

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 states a precise verb+resource (delete a StorageClass) with an explicit guard condition (never one in use by a PVC or PV). It distinguishes itself from siblings by name — create_storage_class for recreation and delete_resource, which it says refuses StorageClass even with allow_bypass.

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?

It spells out exactly when the call is refused (class still in use, default class, failed pre-read) and gives the fallback paths — the Ankra UI or `ankra cluster delete storageclass <name>`. The agent knows both the qualifying conditions and the alternatives ahead of calling.

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