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

Annotations already flag destructiveHint=true and idempotentHint=false, but the description goes well beyond by naming concrete downstream damage: ASSIGN_TAG steps break, leads lose classification, reply-sentiment reporting retroactively changes past numbers, and deleting a campaign's identity tag makes leads indistinguishable in `lead_list`. It also states irreversibility plainly, which is the key behavioral fact an agent needs before invoking.

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?

Front-loaded with the action and its most dangerous side effect, then layers the softer consequences, the confirmation requirement, and the alternative. Every clause carries distinct information with no restatement of the name or title.

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 destructive, non-idempotent, single-param tool with no output schema, the description supplies everything an agent needs: downstream breakage, retroactive reporting impact, irreversibility, the confirmation protocol, and the correct alternative for the non-destructive case.

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?

Only one parameter with 100% schema coverage, and the schema already says 'Tag id, from `tag_list`.' The description reinforces the `tag_list` source but adds no format, casing, or edge-case detail about the id itself, so baseline 3 is appropriate given the schema does the work.

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?

Opens with a precise verb+resource ('Delete a tag') and immediately scopes it against siblings by naming `tag_update` for rename/reclassify and `tag_list` for inspection. An agent can distinguish it from tag_update, tag_create, and tag_list without opening any schema.

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?

Explicitly states the preconditions ('check your flows first', 'show the user what carries it ... get an explicit yes') and names the alternative tool with the condition that selects it ('To rename or reclassify instead, use `tag_update`'). Both when-to-use-with-caution and when-not-to-use are covered.

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