gtm_audit_consent

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

With no annotations provided, the description must convey behavioral traits. It states that the tool scans tags and returns categorized results, implying a read-only, non-destructive operation. However, it does not explicitly confirm idempotency or lack of side effects, which would be beneficial for confidence.

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 a single, well-structured sentence that efficiently conveys the tool's action, scope, and output categories without any extraneous 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?

Given the tool has no parameters and no output schema, the description fully covers its functionality and return structure. It explains both the action and the four categories of results, making it complete for an agent to understand and invoke.

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 input schema has zero parameters with 100% coverage, so the description adds value by confirming that the tool takes no input and performs a comprehensive scan. This clarity goes beyond the schema, which only indicates an empty object.

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 verb 'Scan', the specific resource 'all tags in the sandbox workspace', and the objective 'report consent compliance'. This effectively distinguishes it from sibling tools like gtm_list_tags (which lists tags without compliance analysis) and gtm_create_tag (which creates tags).

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 implies usage for consent compliance auditing but does not explicitly state when to use it versus alternatives, nor does it mention prerequisites (e.g., existence of a sandbox workspace) or when it should not be used. Given the simplicity of a parameterless tool, some guidance on context would be helpful.

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