reelier_diff

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

With no annotations provided, the description fully discloses behavior: it reads from .reelier/runs/<skill>.jsonl, compares per-step outcomes, reports SAME or DRIFTED with reasons, and does not mutate state. It also explains limitations (replay cannot reveal model changes). This is comprehensive for a read-only comparison tool.

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 a single, well-organized paragraph. The first sentence captures the core purpose, followed by details on comparison criteria, usage example, and edge case. Every sentence serves a purpose without redundancy, making it highly efficient.

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?

Despite no output schema, the description explains the return values (SAME or DRIFTED with reasons). It covers file paths, default behavior, legitimate change handling, and when the tool cannot be used (fewer than two runs). For a tool with 4 parameters and no annotations, this is remarkably complete and leaves no critical gaps.

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 covers all 4 parameters with descriptions (100% coverage), so baseline is 3. The description adds value by explaining defaults (baselineIndex and candidateIndex default to last two runs) and the file path pattern. It also gives contextual usage examples, raising the score above baseline but not to 5 since schema already does most work.

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 starts with a clear verb ('Compare two runs') and specific resource ('same skill'), immediately distinguishes from siblings by calling itself a 'drift-detector'. It outlines output ('SAME or DRIFTED') and mentions comparison dimensions (per-step outcomes, structure, heal-level), making purpose unmistakable.

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 provides explicit when-to-use guidance (e.g., 'To check a MODEL upgrade'), explains defaults ('defaults to the last two runs'), and warns when not to use ('Honest when there aren't two runs yet'). It also clarifies what constitutes drift vs. legitimate changes, leaving no ambiguity about proper invocation.

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