Apply manifests to Kubernetes

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

The annotations already signal destructiveness and non-read-only behavior, but the description adds the approval requirement, the failure behavior around validation, and the dry-run execution semantics. These are operational details an agent could not infer from the schema or annotations alone.

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 front-loads the most important risk, then follows a logical order: danger, approval gate, validation prerequisite, and dry-run alternative. Every sentence carries operational weight with no filler.

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, approval-gated apply tool, the description covers the essential workflow: validate, obtain explicit approval, apply, or use dry_run. It is slightly incomplete only because path and namespace semantics are left to inference, but the output schema and annotations cover much of the remaining context.

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 description adds meaningful semantics for approved and dry_run, which are the most sensitive parameters. However, schema_description_coverage is 0%, and path (the only required parameter) and namespace are not explained at all, so the description does not fully compensate for the missing schema documentation.

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 opens with 'DEPLOY. This writes to the cluster and changes running workloads,' which clearly identifies the action, the target resource, and the impact. It also distinguishes itself from sibling tools by directing validation to validate_manifests and framing dry_run as the non-mutating alternative.

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 gives explicit when-to-use instructions: run validate_manifests first, and this tool refuses invalid manifests. It also gives a strict when-not-to-use rule: do not infer approval from the original request. The dry_run path is clearly presented as the safe alternative that needs no approval.

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