Run a safety litmus on a Claude Code skill

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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds extensive behavioral context: it is a static read that does not execute scripts, is fast, and discloses limitations (runtime commands invisible). It also explains the separate 'quality' signal and optional LLM-judged axes. No contradiction with annotations.

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 front-loaded purpose and subsequent details. While every sentence adds value, it is somewhat verbose (multiple paragraphs). A slightly more concise presentation would improve score.

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 one parameter and no output schema, the description covers purpose, checks, limitations, and parameter format. It mentions the safety letter and quality signal but does not explicitly describe the return structure. Overall, it provides sufficient context for effective use.

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% and explains skill_ref as a local path. The tool description adds further value by specifying the v1 format and explicitly stating that remote refs are not yet supported, clarifying usage constraints beyond 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?

The description clearly states that the tool grades a skill against the open static safety litmus, specifying the checks (S-01, S-03, S-04) and differentiating it from behavioral execution. It also distinguishes from sibling tools by focusing on skills, while 'run_litmus' is likely more general.

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 explains when to use the tool (to statically grade a skill) and notes that remote refs are not supported. It implies the tool is not a full safety assessment by stating it is 'NOT behavioral proof,' but does not explicitly list alternative tools or conditions when not to use it.

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