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

Even with annotations present, the description adds meaningful behavioral detail: the created object is a draft, the draft is the only mutable surface, and it must be published before use. It also clarifies that cloneClassifierId copies another classifier's draft config, and that name alone creates an empty draft. This goes well beyond the raw annotations.

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 dense sentences cover purpose, initialization modes, the absence of generate mode, and the subsequent lifecycle, all without wasted words. The most important information is front-loaded and each clause 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?

Given the tool's complexity with five parameters, nested config, and multiple initialization modes, the description is remarkably complete. It explains how to start, what not to attempt, and what to do next with the draft. The presence of an output schema also means return-value explanation is unnecessary here.

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 schema already documents each parameter. The description adds relational and workflow semantics not present in the schema: config and cloneClassifierId are mutually exclusive, name alone yields an empty draft, and clone copies a draft config. This is a meaningful supplement even though the schema already carries the basic parameter descriptions.

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: 'Create a saved, reusable classifier (classify group).' It clearly distinguishes this from sibling tools like create_extractor and create_splitter, and further differentiates by stating 'There is no generate mode (extractors only).' The purpose is immediately unambiguous.

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 explicit setup paths: start from config, clone an existing classifier via cloneClassifierId, or use name alone for an empty draft, and notes that config and cloneClassifierId are mutually exclusive. It also explains the lifecycle by naming the correct sibling tools for editing, publishing, and running, and explicitly warns against expecting a generate mode.

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