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

Description complements the annotations well: it spells out that the draft config is wholly replaced, that published versions are unaffected, and that runs pinned to them keep working. It also warns that destructive replacement is happening, which aligns with destructiveHint=true, and adds the llmContext follow-up behavior not present in 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 sentences, front-loaded with purpose, no filler. The parenthetical get_documentation tip and the immutability note each add meaningful guidance. It is compact but information-dense.

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 annotations, output schema, and schema descriptions, the tool description sufficiently covers the mutation semantics, side effects, scope of changes, and a reference for config format. An agent has what it needs to decide whether to call this tool and what to expect.

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% and parameter descriptions already explain id, name, config, workspaceId, and environment. The description's phrase 'rename it and/or replace the draft config' matches the schema semantics but does not add significant new param-level meaning 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?

The description clearly states the action (update), the resource (classifier's mutable draft), and the specific operations (rename and/or replace draft config). It goes beyond the title by clarifying that only the draft is affected and that published versions are immutable, which distinguishes it from publish_classifier_version and get_classifier.

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 provides clear context: it is for updating a draft, not a published version, and it even includes practical guidance to call get_documentation before hand-editing config. It does not explicitly name alternative tools like create_classifier or publish_classifier_version, but the 'draft vs published' framing strongly implies the intended scope.

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