ml_train_anomaly_detector

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the description's '[Write]' is redundant. The description does not add behavioral context such as whether training overwrites an existing model, how long it takes, or whether it is asynchronous. Given the annotation coverage, the bar is lower, but the description still adds no extra behavioral transparency beyond the structured hints.

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?

The description is a single, focused sentence with an explicit action and resource, plus a '[Write]' tag that reinforces the write nature. It is front-loaded and contains no unnecessary words. Every part earns its place.

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?

This is a training operation with no output schema and no mention of return values, job IDs, or next steps. The description does not explain what the agent should expect after triggering training (e.g., asynchronous job creation, training history). Given the complexity of model training and the absence of an output schema, the description is incomplete.

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?

The schema fully covers both parameters (table and field) with clear descriptions. The description's phrase 'specific table/field' merely echoes the schema without adding new semantics. Baseline 3 is appropriate since the schema does the heavy lifting and the description provides no additional parameter meaning.

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 clearly states the action ('Trigger training') and the resource ('anomaly detection model for a specific table/field'). It distinguishes this from sibling tools like ml_detect_anomalies (which infers) and ml_evaluate_model (which evaluates). The scope is specific and actionable.

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?

There is no explicit guidance on when to use this tool versus alternatives. The description implies usage for training an anomaly detector, but it does not mention exclusions (e.g., 'use ml_train_change_risk for risk models') or prerequisites. It is minimally implied by the tool name and context, but no explicit guidance is provided.

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