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

Annotations already declare destructiveHint=true and idempotentHint=false, yet the description adds substantial context: confirm=false previews which version would go live vs what is live now, confirm=true actually publishes, and staged workspace changes are preserved. This is exactly the extra behavioral detail beyond annotations that matters for a destructive operation.

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 core action and its purpose, then terse safety semantics. Capitalized emphasis is slightly heavy but each sentence carries distinct content with no filler.

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 publish-overriding tool with an output schema, the description covers preview/publish behavior and the persistence of staged changes. The only shortfall is the undocumented container parameter, otherwise self-sufficient.

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 0%, so the description must carry parameter meaning, and it explains the two most consequential ones well: confirm as preview-vs-publish and version_id as coming from list_gtm_versions. The container parameter is left undocumented, leaving one gap.

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 (rolls back) and resource (GTM container version) with clear framing as 'the undo for a bad publish'. It distinguishes itself from the forwarding sibling publish_gtm_container by naming the opposite direction of action, so an agent can tell them apart without opening either 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 clear context (undo a bad publish, site immediately serves known-good config) and points to list_gtm_versions as the source for version_id. It does not explicitly name publish_gtm_container as the forward alternative or state exclusions, so it stops short of the 5-level routing guidance.

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