Tag Manager workspace changes

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

The description expands on the read-only behavior by detailing the returned data: 'Returns the list of entities (tags, triggers, variables) added, modified, or deleted relative to the live published version, plus any merge conflicts.' It also explains the is_clean flag semantics. This is consistent with the annotations (readOnlyHint=true, destructiveHint=false) and adds useful output context.

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 description is concise and front-loaded. The first sentence states the purpose, the second details the output, the third provides a usage scenario, and the fourth explains the is_clean field. Every sentence adds value with no fluff or redundancy.

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?

While the purpose and output are covered, the description is not fully complete because it omits parameter explanations and does not provide a full output schema. A user may not know how to correctly invoke the tool, especially with the optional parameters, and what exact structure the returned entities have. The description relies on prior knowledge of GTM workspaces.

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?

The schema description coverage is 0% for parameters, and the description does not compensate. workspace_id, gtm_account_id, and gtm_container_id are not explained at all. Even though the names are somewhat self-explanatory, the role of optional parameters like gtm_account_id and gtm_container_id, and their relationship to workspace_id, is ambiguous. This is a significant 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?

The description clearly states the tool's purpose: 'Show drafted-but-not-published changes in a GTM workspace.' This specifies both the action (show) and the resource (GTM workspace changes). It also differentiates from sibling tools like list_gtm_workspaces by focusing on the diff between the draft and published versions.

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?

The description provides a concrete use case: 'Common cause of "I edited a tag but nothing happened" — the workspace was never published.' This helps users understand when to use the tool. While it doesn't explicitly name alternative tools, it implies the scenario where checking uncommitted changes is needed, which is sufficient context.

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