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

Annotations already flag destructiveHint=true and non-idempotent, but the description adds meaningful behavior the annotations cannot: confirm=false previews versus confirm=true applies. It stops short of noting permission/auth requirements, keeping it at a strong 4 rather than 5.

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 tight clauses front-load the mutation, then the per-action requirements, then the safety toggle. No filler and no sentence that fails to carry information.

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 an 8-param destructive operation with an output schema present, the description covers actions, permission vocabularies, and the preview/apply gate, so nothing critical for a correct call is missing. The ambiguous 'account' parameter is the one loose end.

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?

With 0% schema coverage the description does real work, enumerating the enum values for account_permission (user|admin|noAccess) and container_permission (read|edit|approve|publish) and tying email/container_id/permission_path to their actions. The 'account' parameter is only implied by the scope phrase and never explicitly documented, so it is not fully compensatory.

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 specific verb pair (GRANTS/REVOKES) and the exact resource (a user's access to a GTM account/containers). An agent can immediately distinguish this from sibling read tools like list_gtm_permissions.

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 branches on action='grant' vs 'revoke' and states what each requires, and it routes the agent to list_gtm_permissions to obtain permission_path. That is a concrete when-to-use plus an alternative source.

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