jev_triage_failure

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

No annotations are provided, so the description carries the full burden. It discloses that the tool is 'cheap' and 'probabilistic', returns 'structured likelihood signals', and explicitly does not diagnose or fix. This is meaningful behavioral context beyond the schema. It could add more about caching or side effects, but the core behavior is well disclosed.

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, each earning its place: what it is, when to use it, and what it returns/doesn't do. The key information is front-loaded. No redundancy or filler.

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?

The tool has an output schema, so return values are documented elsewhere. The description covers purpose, usage timing, and limitations. It doesn't mention the 'use_cache' parameter or how the tool handles previous_failure, but for a triage tool with a clear scope, the description is largely complete. The main gap is that it doesn't explain what inputs are most important to provide, but the schema covers the input structure.

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. The description explains the tool's overall purpose but does not explain any of the 8 parameters (task, current_step, failure, use_cache, diff_summary, changed_files, previous_failure, client). The parameter names are fairly self-explanatory, and the schema has detailed nested definitions, but the description adds no parameter-level meaning. Baseline 3 is appropriate because the schema itself is rich, but the description does not help with parameter semantics.

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 states a specific verb ('triage'), a resource ('test/build/lint/typecheck failures'), and a clear scope ('probabilistic', 'cheap'). It also explicitly distinguishes itself from diagnosis/fixing, which helps an agent understand exactly what this tool does and does not do.

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 says 'Use before broad reasoning when the relationship or scope of a failure is unclear.' This gives a clear when-to-use condition. It also states what the tool does not do ('does not diagnose or fix the problem'), which helps an agent avoid using it for the wrong purpose. Sibling tools are not named, but the usage context is specific enough to route correctly.

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