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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond annotations by emphasizing versions are published and immutable, and by warning that results may include llmContext guidance that the agent should follow. This is useful operational behavior not present in the schema or 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?

The description is three short sentences with no filler. It front-loads the core purpose, then adds the relevant sibling reference and an important output-behavior instruction. Every sentence 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?

The description covers the essential purpose, directs the agent to the right sibling for fetching configs, and mentions the unusual llmContext guidance behavior. The output schema and 100% parameter coverage supply the remaining details like pagination and defaults. It is slightly less complete than it could be regarding pagination workflow, but not deficient.

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 100%, so the schema already explains all six parameters, including defaults and the meaning of environment and workspaceId. The description adds no additional parameter-level semantics beyond mentioning published versions, which is appropriate given complete schema coverage. Baseline 3 applies.

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: 'List a classifier's published (immutable) versions.' It distinguishes itself from closely related siblings like get_classifier and list_classifiers by narrowing scope to published versions and noting immutability. The '(classify group)' qualifier adds domain context that helps orient the agent.

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 context for when to use the tool: when listing published versions of a classifier. It also points to get_classifier as the alternative for fetching a single version's config, which helps the agent choose between sibling tools. It does not explicitly state when NOT to use it, but the alternative reference is strong enough guidance.

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