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

Annotations already cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true). Beyond that, the description discloses two behaviors the agent would otherwise have to guess: the trigger is written to the draft workspace rather than live, and required built-in variables are enabled automatically as a side effect — a meaningful mutation of container config. It stops short of describing error modes or permission requirements.

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?

Two dense sentences, front-loaded with the verb and destination scope, then the type list. Nothing is redundant with the title and no filler words are present.

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 a nine-parameter mutation tool with no output schema, the description supplies the essential context: draft scope, supported types, URL-based conditions, and automatic variable enabling. What is missing is the conditional relationship between certain types and their required parameters, which the agent must infer from the schema field descriptions.

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?

With 67% schema coverage, the description adds real meaning: it maps the 'type' enum values to human concepts, notes URL matching for page views (feeding the 'conditions' array), and names built-in variables such as Click URL and Form ID that are relevant to conditions.variable. It does not clarify the type-specific pairings (event_name for custom_event, scroll_percentages for scroll_depth), leaving that partly to the schema.

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 trigger') and then enumerates the supported trigger types, so an agent can immediately tell this apart from gtm_create_tag or gtm_create_variable. It also names the target scope (workspace DRAFT), which sharpens the purpose further.

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 mention of 'workspace DRAFT' implies the draft-then-publish workflow and hints that gtm_publish follows, but the description never says when to choose this tool over siblings like gtm_create_tag or gtm_create_variable, nor does it state prerequisites or exclusions. Usage is implied rather than directed.

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