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

Annotations already mark this as non-read-only and destructive, so the description's added value is scoping the mutation: only the draft config/name changes, while published versions and runs pinned to them keep working. This prevents an agent from assuming a destructive update invalidates deployed artifacts. 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?

The description packs purpose, scope, and a documentation pointer into two sentences. The parenthetical phrasing ('classify group', 'hand-editing it?') is slightly compressed, but each clause carries information and there is no padding.

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 5-param schema, full schema documentation, an output schema, and annotations, the description covers the only semantic nuance an agent needs: draft-only mutation and published-version immutability. It also points to docs for hand-authored config. Nothing necessary for correct invocation is missing.

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 baseline is 3; the description reinforces that name maps to renaming and config maps to replacing the whole draft. It adds a pointer to external documentation for config shape, but does not materially extend what the schema already provides. This is adequate without being strongly additive.

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 action ('Update') on a specific resource ('a classifier's mutable draft') and spells out what that means: rename it and/or replace the draft config. The phrase 'Published versions are immutable and unaffected' separates it from publish_classifier_version and related version tools. This is unambiguous even among many update_* siblings.

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?

Tells the agent the operation applies only to the mutable draft, not to published versions, and warns that runs pinned to published versions are unaffected. It also supplies a when-to prerequisite: if hand-editing the config, call get_documentation with the configuration link first. It does not explicitly name a sibling for publishing a new version, but the draft-vs-published distinction is enough to route the call correctly.

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