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

Annotations already declare this is a non-read-only, non-idempotent, non-destructive creation. The description adds genuinely useful context beyond them: ~1 minute training time, dependence on the account's NEXUS plan, and the Free-plan cap of 1 classifier. It does not explain what happens on plan-limit exhaustion or what the response contains.

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 dense sentences with zero padding. The purpose and constraints lead, followed by cost/latency facts, so the most decision-relevant information is front-loaded.

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 creation tool with no output schema, the description covers constraints, latency, and plan gating. The only notable omission is what the call returns (e.g., a classifier identifier) needed to chain into decide_predict or get_decide_classifier.

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%, so the baseline is 3, but the description adds constraints the schema does not carry: at least 2 examples per label and a maximum of 255 labels. This materially shapes how examples must be composed.

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 concrete verb and resource ('train a text classifier') with scope qualifiers (labelled examples, label limits), so an agent can distinguish it from get_decide_classifier or list_decide_classifiers at a glance. It stops short of explicitly naming the sibling read tools as alternatives.

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?

Usage is implied by the resource name and the example requirements, but there is no explicit when-to-use or when-not-to-use guidance, and no alternative tool (e.g., decide_predict for inference, get_decide_classifier for retrieval) is named. The constraints hint at the context without routing the agent.

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