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

Annotations only declare destructiveHint=true; the description goes well beyond by explaining that messages survive, that the affected count is returned, matching semantics, system-label refusal, silent no-op on no match, the gmail.modify/reconnect requirement, and irreversibility. This is a rich disclosure that the annotation alone does not carry.

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?

Dense but every sentence carries distinct information: scope, side-effect, matching rule, refusals, auth, and the safety warning. The most consequential facts (definition only, irreversible) are front-loaded and the confirm-first instruction closes it.

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?

No output schema exists, yet the description tells the agent a count of affected messages is returned. For a two-parameter destructive tool, the safety, auth, and matching details leave nothing an agent needs in order to call it correctly.

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 are already documented, including the exact-match, case-insensitive rule for `name`. The description restates those semantics and adds the multi-account trigger for `account`, which is useful but largely mirrors the schema — baseline 3 applies.

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 verb and resource ('Delete a Gmail label DEFINITION by name') and immediately disambiguates from the message-deleting siblings by clarifying that carried messages are NOT deleted. An agent can distinguish this from delete_message, trash_message, and update_label 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?

Gives strong operational context: when to pass `account`, that system labels are refused, that non-matching names are no-ops, the gmail.modify requirement, and to confirm with the user first. It never names an alternative tool (e.g. update_label for renaming) or the when-not-to-use case explicitly, keeping it just below full marks.

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