curator_run

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

With no annotations, the description fully discloses all behavioral traits: the full lifecycle (active→stale→archived), tier-specific adjustments (validated never ages, hypothesis ages faster), exclusion rules, the side effect of moving primary directory to .archive/, and the dry_run vs apply behavior. This is exceptionally transparent.

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 is well-structured with sections (Lifecycle, Tier-aware adjustments, NEVER touches, dry_run) and front-loaded with the main verb. It is relatively long but every sentence adds unique value; no redundancy. A slight trim could improve conciseness, but it is clear and organized.

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 tool with three parameters and complex behavior (lifecycle, tier logic, exclusions, dry_run), the description covers all necessary facets. An output schema exists (context signal), so explaining return values is not required. The description is complete for correct selection and invocation.

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 schema has 0% description coverage, placing full burden on the description. The description explains the two numeric parameters (stale_after_days, archive_after_days) within the lifecycle context, clarifying their roles. The dry_run parameter is explicitly described: reports without writing vs applying. While it doesn't give explicit ranges or formats, the names and context suffice for correct use.

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 a specific verb+resource: 'Move stale agent-created skills to archive.' This clearly distinguishes curator_run from siblings like curator_review (which reviews candidates) and other tools. The lifecycle and exclusions further reinforce the exact purpose.

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 explicitly states when to use (moving stale skills) and especially what it NEVER touches (foreground, pinned, validated, unknown provenance), giving clear when-not-to-use guidance. It also explains the dry_run mode and how tier adjustments affect aging windows, providing comprehensive context for appropriate invocation.

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