laya_triage

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

With no annotations, the description carries the behavioral burden. It does disclose that this is a one-pass probabilistic classifier and that low confidence should trigger human escalation. However, it does not mention whether the call is read-only, what failure modes exist, or any rate/auth constraints, leaving some behavioral context implicit.

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, front-loaded with the core action, and every clause adds useful information. There is no filler or 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?

The tool is simple and has an output schema, so the main intent, outputs, and usage are covered. But the unexplained optional timeout_ms, combined with zero annotation support, means an agent still needs to infer part of the calling contract.

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 implies the required 'text' parameter through 'message or ticket', but it never explains the optional 'timeout_ms' parameter or how it affects the call. This leaves part of the parameter surface undocumented.

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 and resource ('Triage a message or ticket') and enumerates the exact outputs: intent, urgency, frustration, refund request, churn risk. It also clarifies it returns probabilities per aspect in a single pass, which separates it from generic classify/decide siblings even without naming them.

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?

It gives explicit when-to-use guidance: use it to route or prioritize before an expensive agent turn, and escalate to a human when confidence is low. It does not explicitly name alternative tools or state when not to use it, so it falls just short of a 5.

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