rms_prune

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

With no annotations, the description carries the full burden. It discloses the critical safety behaviors: defaults to a dry run and never deletes notes. It also specifies the archive destination. It does not clarify whether archiving moves or copies notes, and omits permission requirements, but the core safety profile is transparent enough for safe invocation.

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?

Two sentences, no fluff. The first sentence captures purpose and the dry-run default; the second reinforces the non-destructive nature. Key constraints are front-loaded, and every word earns its place.

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 three-parameter tool with all optional params and no output schema, the description covers the essential intent and safety. It leaves out details like the project parameter's fallback usage and the exact output/return behavior, but those are either in the schema or not critical for correct invocation. The description is sufficiently complete for an agent to call the tool safely.

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 100%, so the schema already documents all three parameters. The description adds minimal extra meaning—it maps 'apply=true' to the archive action and 'retention window' to age, but these are largely redundant with the schema descriptions. It does not elaborate on the `project` parameter's purpose beyond what the schema states.

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The description states a specific verb ('Find'), a precise resource ('superseded vault notes'), a retention condition ('older than a retention window'), and an optional action ('archive them'). It also clearly distinguishes itself from sibling tools like rms_search and rms_code_search by focusing on pruning/archiving, not retrieval or editing.

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 clearly implies when to use the tool (to identify and optionally archive superseded notes) and explicitly states the dry-run default and the `apply=true` switch to finalize. It does not explicitly name alternatives or say 'do not use when...', but the purpose is self-evidently distinct from the search and write tools.

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