GTM API: free-form request

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

Annotations already declare destructiveHint=true and openWorldHint=true, and the description adds the crucial non-obvious behavior that DELETE without confirm=true is a preview that deletes nothing. It also carves out publishing as out of scope. It does not mention auth scopes or how API errors surface, so it is strong but not exhaustive.

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: what it is and where it points, examples of paths, then the two safety caveats. No filler and the escape-hatch framing is front-loaded.

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 free-form proxy with no output schema, an agent has enough to construct a call and understands the destructive gate. The main remaining gap is return-shape or error expectations for arbitrary endpoints, which is left implicit.

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 75% schema coverage, the schema already documents body, path, and confirm. The description still adds real value by giving concrete path strings that clarify the 'relative to /tagmanager/v2' convention and by reinforcing the confirm preview/delete split in behavioral terms.

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?

The description names the exact API surface (Tag Manager API v2, www.googleapis.com/tagmanager/v2) and states it is the escape hatch 'for anything without its own tool', then gives three concrete path examples spanning GET, POST sync, and POST templates. That contrasts it cleanly with the many specific gtm_* siblings.

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 selection rule explicitly: use this when no dedicated tool exists, and it names a hard exclusion ('Publishing only via gtm_publish_version'). The path examples show the expected shape for both read and mutation calls.

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