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

Annotations provide only readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false. The description goes well beyond these: it reveals that the draft is the only mutable surface, that name alone yields an empty draft, that there is no generate-mode fallback, and that llmContext guidance in results should 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?

Every sentence earns its place: purpose, creation modes with prerequisite, exclusion, lifecycle routing, and result guidance. It is front-loaded with the core purpose. It loses a point for density — the mutually exclusive modes and lifecycle routing are packed into long clauses that would be more scannable as bullets or separate sentences.

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?

For a 5-parameter, nested-object creation tool, the description covers the full decision space: how to start (config, clone, or name-only), what not to do (no generate mode), what happens next (update/publish/run), and where to get authoritative config docs. An output schema exists, so return-value explanation is unnecessary. Nothing an agent needs to call this correctly 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 coverage is 100%, so the baseline is 3. The description adds real value on top: the mutual exclusivity of config vs cloneClassifierId (not stated in the schema), the 'name alone creates an empty draft' default that explains what happens when both optional params are omitted, and the confirmation that generate-mode is absent. This justifies a 4.

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+resource: 'Create a saved, reusable classifier (classify group)'. It distinguishes itself from sibling creation tools (create_extractor, create_splitter, create_workflow) by scoping to classifiers and further clarifies the creation step from lifecycle siblings: 'edit it with update_classifier, freeze it with publish_classifier_version, run it with classify_document'.

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?

It explicitly states the two valid creation modes and their exclusivity: 'Start from config ... or cloneClassifierId ... — mutually exclusive'. It gives a prerequisite ('call get_documentation ... before hand-authoring one'), an exclusion ('There is no generate mode (extractors only)'), and a default behavior ('name alone creates an empty draft'). An agent knows exactly when and how to invoke this tool.

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