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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the description adds real value by disclosing that writes land in the workspace DRAFT, that publishing is required separately, and that a Conversion Linker is auto-created for Google Ads if missing — an important implicit side effect. It still does not say what happens on name collisions or whether partial failures roll back, so not a top score.

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?

Three short sentences, zero filler, with the core action and platform scope front-loaded and the publish caveat trailing where it belongs. Every sentence carries distinct 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?

For an 18-parameter mutation tool with platform-dependent requirements and no output schema, the description covers the workflow and one side effect but leaves the platform-to-parameter mapping and failure behavior unaddressed. Adequate to start, insufficient to invoke confidently across all five platforms.

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 covers 72% of parameters, so the baseline is 3, and the description's mention of "thank-you page, dataLayer event or click" loosely maps to the `when` enum without naming its values. Critically, it never explains that many of the 18 parameters are platform-conditional (pixel_id/pixel_event for Meta, conversion_id/conversion_label for Google Ads, measurement_id/event_name for GA4), which is the main semantic risk when invoking this tool.

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 states a specific verb (create) and concrete resources (trigger + conversion tag) across named platforms, and the phrase "One step" distinguishes it from the separate gtm_create_trigger / gtm_create_tag siblings. An agent can tell what it produces without opening the schema.

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 implies usage through the workflow note that nothing goes live until gtm_publish, and the DRAFT scoping tells the agent this is a staging step. However, it never says when to prefer the granular gtm_create_trigger/gtm_create_tag tools instead, nor what to do if the trigger already exists; guidance is implied rather than explicit.

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