skill.reliability

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

No annotations exist, so the description carries the full burden. It does disclose a genuine behavioral trait beyond the schema: the MODELBOUND_API_KEY auth requirement, plus the fact that data is a rolling window of real-use outcomes. It does not say whether results are per-skill aggregates or per-run records, how they are ordered, or what happens when no data exists for the window.

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 short sentences, front-loaded with what it returns, then when to use it, then the auth prerequisite. No filler and no repetition of the tool name.

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 two-parameter read tool with no output schema, the description covers purpose, outcome vocabulary, usage intent and auth. It stops short of explaining the shape of the returned reliability data, which is the main remaining gap given there is no output schema to lean on.

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%: both 'days' (default 30) and 'skill_id' (optional Skill UUID) are fully documented in the schema. The description adds only the notion of a rolling window, which the schema already conveys; baseline 3 applies.

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 specific verb ('Read back'), a specific resource (team skill performance), and a concrete outcome taxonomy (worked / partial / failed) over a defined window. The phrase 'in real use' separates it from synthetic-evaluation siblings like skill.benchmark, eval.run and skill.compareVersions.

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?

Gives two explicit use cases: picking the most reliable skill for a task, and finding skills that need attention. It does not, however, name a specific alternative or state when NOT to use it (e.g., when to prefer skill.benchmark or skill.testRuns instead).

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