prune_backups

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

With no annotations provided, the description carries the full burden. It explicitly discloses that dry_run defaults to True, what response shows (what WOULD be deleted), and the deletion semantics for dry_run=False. It also explains the auto-retention vs manual stage behavior. Minor gap: doesn't mention whether deletion is reversible or what the response includes beyond 'what would be deleted'.

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?

Well-organized with a clear lead sentence, then default-behavior context, then a paragraph on stage semantics, then Args section. Slightly verbose in the Args section repeating schema defaults, but each section earns its place and the structure is scannable.

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-adjacent tool (deletion operation) with no annotations, the description thoroughly covers the safety default (dry_run), the stage scoping rules, and parameter constraints. An output schema exists, so return-format details aren't required. This is comprehensive for a 3-param tool.

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 description coverage is 0%, so the description must compensate. It does: explains keep_last_n must be >= 0, enumerates valid stage values (session/weekly/monthly/manual), and clarifies dry_run's True/False semantics with defaults that match the schema. Adds meaning well beyond the bare 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?

Description uses specific verb+resource 'Remove older backups, keeping the most recent N per stage'. It clearly distinguishes scope (per-stage retention) and explicitly differentiates from siblings like create_backup and list_backups by describing the pruning behavior.

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?

Provides explicit when-to-use guidance: dry_run default behavior, how to target manual backups explicitly with stage='manual', and the safety mechanism for confirmation before committing. It also states that manual backups are never auto-pruned, giving clear exclusions.

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