Delete a category or label

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

The annotation already provides destructiveHint=true, so the agent knows deletion is destructive. The description adds critical behavioral detail: categories moves feeds to default (no data loss), labels are detached only, the two-step confirmation flow, and the matching order between categories and labels. This goes well beyond the annotation, scoring high.

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 sentences, front-loads the core action, and each sentence adds unique value (behavior for category vs label, naming collision, confirmation flow). No wasted words; could be slightly more compact but is well within reasonable length.

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 tool has 2 parameters, destructiveHint annotation, and no output schema, the description covers the key behaviors: what happens to associated data, the two-step confirmation, and the naming ambiguity. For complexity level, this is nearly complete; only missing details like error cases or permissions.

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 both parameters (name, confirm_token) are documented in the input schema. The description adds context that 'name' must match exactly from list_categories, and that 'confirm_token' comes from a first call. This adds value beyond schema, but not enough to raise above baseline 3 given good schema already.

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 that the tool deletes a category or label, and it distinguishes the behavior between categories (feeds move to default, no articles lost) and labels (detached from articles). However, it does not explicitly differentiate from siblings like rename_category_or_label or other deletion tools, though the scope is specific enough.

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 explains when to use this tool (to delete categories or labels), mentions a naming collision caveat (categories matched first), and describes a two-step process with confirmation token. It does not explicitly state when not to use it or list alternatives, but the two-step guidance helps the agent select and invoke correctly.

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