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

Goes well beyond the annotations by disclosing a non-obvious side effect: the first write to a container creates a draft workspace named AdCopilot if none exists. It also explains the safety model — no publish permission, so nothing reaches the website until a human publishes — which is exactly the context an agent needs before a write it cannot undo via this tool.

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?

The staging constraint is front-loaded and capitalized, and the two paragraphs map cleanly to 'what it does' and 'what happens on the backend'. The trailing 'Tools revision: d80f65c0.' is pure noise that earns no place in an agent-facing definition.

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?

An output schema exists, so return values need not be described, and the publish-safety model is fully covered. However, for a creation tool whose `parameter` argument is a free-form array and whose `type` string drives the whole result, the definition leaves an agent unable to construct a valid call without external GTM knowledge.

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% across four parameters, including an untyped `parameter` array with no item schema, so the description carries the burden and does not meet it. It never states the accepted `type` values, whether `container` is an ID or path, or what shape `parameter` entries should take; only the word 'container' is given incidental meaning.

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 and resource ('Create a user-defined variable') and scopes it precisely as STAGED in the AdCopilot workspace. The qualifier 'user-defined' implicitly distinguishes it from the built-in-variable sibling (gtm_enable_built_in_variable), and the 'never published' clause separates it from anything that would go live.

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?

Usage is implied by the verb and resource rather than stated: there is no explicit 'use this when...' or guidance on choosing between this and gtm_create_tag/gtm_create_trigger/gtm_update_variable. The second paragraph explains the side effect of calling it, which helps an agent anticipate consequences, but not the decision of when to call it.

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