jev_triage_test_failure

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

Annotations are absent, so the description carries the full burden of behavioral disclosure, and it delivers: it reveals a 70-300ms latency bound, states the tool is zero-generation (no frontier LLM call), and explains the semantic of the skip_llm flag (true when resolvable deterministically). It stops short of declaring safety/side-effect behavior or error handling, but for a diagnostic triage tool this is strong coverage.

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?

Two sentences, roughly 50 words, with the primary verb and resource front-loaded in the first sentence and the return contract in the second. Every piece — input types, mechanism, latency, and output semantics — earns its place, and nothing is repeated from structured fields.

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?

Given no output schema and no annotations, the description correctly compensates by explaining what the tool returns (root cause category, skip_llm flag with meaning, action recommendation) and its execution characteristics. The tool is simple (one parameter, fully documented), so the only missing context is limited to untested edges like malformed input handling, which is minor.

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 coverage is 100%, with failure_log already described as 'Raw test failure output, stack trace, or compiler error log', so the schema does the heavy lifting. The tool description echoes these input types in its purpose sentence, reinforcing alignment but adding no new format, constraint, or preprocessing information. Per the baseline rule for high schema coverage, 3 is appropriate.

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 opens with a specific verb ('Triages') and a specific resource domain ('test traceback, compile error, or runtime failure'), which lays out exactly what the tool consumes. The output fields it names (root cause category, skip_llm flag, action recommendation) further pin down the tool's role. None of the siblings (abort_check, route_task, verify_completion, etc.) perform triage of failure logs, so an agent can distinguish this tool without opening the schema.

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 gives clear when-to-use context by enumerating the specific inputs it handles: test tracebacks, compile errors, and runtime failures. It does not name explicit alternatives or state explicit exclusions, but the input domain is stated explicitly enough that routing against the listed siblings is straightforward.

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