Audit a container workspace

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

Annotations already cover safety (readOnly, idempotent, non-destructive), so the description's value-add is the request-cost profile ("4–6 requests total") and the scope of what is examined. That is meaningful context beyond the structured fields, though it doesn't say whether results cover only the default workspace vs. drafts or how findings are aggregated.

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?

Front-loaded with the core instruction and rationale in the first clause, then a compact enumeration of checks and a format hint. Slightly telegraphic ("UA leftovers", "dangling/unused triggers") but every fragment carries information.

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 structure needn't be described, and the container identifier format is supplied. The remaining gap is the role of the optional workspace parameters, which matters for a tool whose whole point is auditing a specific workspace scope.

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% and there are 3 parameters, so the description must compensate. It does so for `container` by giving accepted formats (GTM-XXXXXXX or accounts/<a>/containers/<c>), but says nothing about `workspace_id` or `include_workspace_status`, leaving two parameters undocumented anywhere.

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 concrete verb+resource (one-shot health check of a workspace) and enumerates the specific defect classes it detects (UA leftovers, duplicate Google tags, dangling triggers, undefined variables, paused tags, unpublished changes). It also explicitly positions itself against the family of single-resource list tools, so an agent can tell it apart from gtm_list_tags/gtm_list_triggers without inspecting schemas.

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?

"prefer this over many single list calls" plus the 4–6 request cost note gives a clear selection rule against the sibling list tools. It does not state when *not* to use it (e.g., auditing a specific tag only), but the usage context is unambiguous for the common case.

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