skill.test

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

With no annotations, the description carries the full burden, and it does disclose the key trait that execution is against a live model (implying real cost/latency/non-determinism) plus the shape of what comes back. It omits auth requirements, rate limits, and any failure/timeout behavior.

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?

Three sentences, zero filler, purpose stated first and the mode-selection rule immediately after. Every clause carries information an agent needs.

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?

With no output schema, the description usefully names the return fields (adherence_score 1-10, verdict, latency_ms) and the live-model behavior. But for a 4-param, 0%-coverage tool with no annotations, the unexplained required skill_id and absent failure/cost semantics leave 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?

Schema description coverage is 0%, so the description must compensate. It explains the relationship among test_case_id, prompt, and skill_md (mutually exclusive modes), but never addresses skill_id, which is the sole required parameter. Partial compensation only.

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?

States a concrete verb+resource+"single" scope ("Run a single skill test case against the live model"), which implicitly separates it from plural/reporting siblings such as skill.testRuns and skill.testCases. It does not explicitly name an alternative, so sibling differentiation is inferred rather than stated.

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 routes between two invocation modes ("Pass test_case_id for a saved case or prompt + skill_md for an ad-hoc run"), which is real usage guidance for choosing inputs. However, it never says when to reach for this tool versus neighbors like eval.run, skill.benchmark, or skill.testRuns.

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