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

With annotations only covering readOnly/openWorld/destructive, the description adds the material behavior: nothing is published, no Google login is required in the browser, the preview is a point-in-time snapshot that goes stale after each edit, and anyone holding gtm_auth can view the unpublished state ('nicht öffentlich teilen'). That security and staleness disclosure is exactly what annotations cannot express.

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?

Purpose is front-loaded in sentence one, followed by return values, testing recipes, and caveats in a logical order. It is on the long side and the returned-field enumeration is partly redundant given an output schema exists, but no sentence is 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 2-parameter tool with an output schema, annotations, and no nested objects, the description covers everything an agent needs: what it produces (gtm_auth, gtm_preview, script_url with gtm_cookies_win=x), how to consume it, error branches, and the data-sensitivity caveat.

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 all parameter meaning, and it does: workspace_id comes from gtm_list_workspaces, must be purely numeric or the call returns {"error":"invalid_id"}; workspace is the customer slug and is optional when only one workspace exists.

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The opening sentence states a specific verb and resource: it makes an unpublished GTM workspace state testable without publishing. It immediately separates the tool from siblings like gtm_publish_version or gtm_create_version by naming exactly what it does NOT do.

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 gives concrete usage contexts (Playwright request redirection, or a staging page loading the container with gtm_auth/gtm_preview) and mandates re-calling after every workspace change. It also routes failure cases to alternatives (gtm_sync_workspace on merge_conflict, gtm_list_tags/gtm_list_triggers on compiler_error), though it does not explicitly say when to pick a sibling over this tool.

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