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

Annotations already state readOnlyHint=false and destructiveHint=false. The description adds valuable behavioral context: versions are immutable, publishing operates on the draft unless a config is passed, and llmContext guidance may need to be followed. No contradiction with 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?

Four sentences, front-loaded with the core purpose. Each sentence earns its place, but the phrase '(classify group)' is slightly ambiguous and the final llmContext instruction, while useful, reads as generic. Overall compact and structured.

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?

With a complete schema (100% parameter coverage), output schema present, and annotations provided, the description covers purpose, behavior (immutability), and the config override option. It omits edge cases like failure conditions or permission prerequisites, but those are partially covered by schema descriptions (workspaceId and environment). Adequate for a publish operation.

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%, with each parameter already described. The description adds a small amount of reinforcement ('releaseType picks the major or minor bump; pass config to publish that config instead of the draft') but does not substantially extend beyond what the schema already provides.

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?

States a specific verb ('Publish'), resource ('classifier's current draft config'), and outcome ('new immutable semver version'). Clearly distinguishes from related operations like create_classifier or update_classifier by focusing on versioning. The mention of pinning in runs and evaluations adds further specificity.

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?

Implies when to use this tool: when a stable, immutable classifier version is needed for pinning, vs iterating on the draft. It does not explicitly name alternative tools (e.g., update_classifier, create_classifier, publish_extractor_version), but the workflow context ('Published versions never change — keep iterating on the draft') provides clear usage framing.

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