delete_tag

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

Annotations already mark destructiveHint=true and readOnly=false, so the description's warning is consistent with the structured metadata. It adds valuable behavioral context by disclosing the cascade effect: the deletion propagates to all documents using the tag and is permanent. This goes beyond what the annotations alone state.

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 short sentences, front-loaded with the destructive warning, with no filler. Every clause either states the action, the consequence, or the caution.

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 simple destroy operation, the combination of description and schema covers the target entity, the global cascade, the permanence, the confirmation requirement, and the safety profile. No output schema is needed, and an agent has enough information to decide whether to call the tool and what to pass.

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?

The description does not directly explain the `id` or `confirm` parameters, and the schema only documents `confirm` (50% coverage). It does add implicit meaning by defining what object is being deleted, which makes `id` interpretable as the tag identifier, but it does not compensate for the undocumented `id` field. The warning also provides context for why `confirm` exists, though the schema already states its requirement.

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 an explicit verb and object ('Permanently delete a tag') and clarifies the scope ('from the entire system'). It differentiates itself from sibling read/update tools (list_tags, get_tag, update_tag) by emphasizing permanent, system-wide deletion.

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 destructive consequence ('remove the tag from ALL documents') gives the agent a clear condition to evaluate before choosing this tool, and 'Use with extreme caution' is an explicit warning. However, it does not name any alternative (e.g., update_tag) or state when not to use it, so usage guidance is mostly implied rather than explicit.

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