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

Annotations only say it is a non-read-only, non-destructive, non-idempotent write. The description adds real behavioral context: the policy is written through GitOps, omitted fields are preserved rather than reset, databases=false silently drops all database contents from restore points, and the required permission is backups.manage. That is beyond what the structured fields disclose.

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?

Three dense sentences, front-loaded with the primary action and effect, then the merge/omission rules, then the permission requirement. Slightly long clauses but every sentence carries operational information for a 10-parameter tool.

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 mutation tool with 10 parameters, nested retention object, no output schema and only partial annotation coverage, the description covers side effects, defaults, cross-parameter constraints, and authorization. It does not address failure modes or what happens if the cluster/GitOps write fails, which is the main remaining gap.

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 baseline is 3, but the description adds cross-parameter meaning: the databases/confirm_exclude_databases coupling and the rule that omitting both databases and persistent_volume_claims preserves the stored policy. Useful integration detail beyond the per-field schema text, though some of it is duplicated in the 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?

States a specific verb and resource ('Turn on scheduled backup protection for a stack') and even explains the mechanism (policy written via GitOps, the ankra-backup stack takes the captures). This clearly separates it from siblings like unprotect_stack, create_stack_restore_point, or provision_backup_vault.

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?

Explains the operational conditions: omitted fields keep the stored policy, databases=false requires confirm_exclude_databases=true, and the call needs backups.manage. It does not explicitly name alternatives (e.g. unprotect_stack to reverse it, or create_stack_restore_point for a one-off capture), so routing guidance is implied rather than spelled out.

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