Create version from workspace (🟡 write)

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

The annotations only say write/openWorld/non-idempotent; the description adds the critical side effect that the workspace is deleted and a fresh default one created, plus that conflicts block the operation. That is exactly the beyond-annotation context an agent needs. Minor tension: destructiveHint=false while the text describes workspace deletion, though in GTM terms the content is preserved in the snapshot, so this is a caution rather than a contradiction.

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 sentences with the most decision-relevant fact (not published) front-loaded. No filler, and the caveats are ordered by importance: side effect, then blocking condition, then safe-inspection path.

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 mutation tool with an output schema, this covers the essential behavior: what is created, what is destroyed, what blocks it, and how to preview. The remaining gap is parameter-level detail (name/notes/workspace_id) that neither the schema nor the description supplies.

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 description coverage is 0%, so the description must carry the parameter burden. It does well for dry_run (semantics plus default), but name, notes, container, and workspace_id are left entirely unexplained — notably whether workspace_id omitted means the default workspace.

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?

"Snapshot the workspace into a container version" names a specific verb and resource, and "(NOT published yet)" immediately separates it from the sibling gtm_publish_version. An agent can route between create_version and publish_version 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?

It states the preconditions for a successful call (merge conflicts block it) and points at dry_run=true as the inspection path, which is real when-to-use guidance. It stops short of explicitly naming the alternatives (gtm_publish_version, gtm_get_workspace_status) that an agent should reach for first.

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