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

Annotations already establish readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds non-obvious behavioral detail: the response flattens each variable's `params` (e.g. a constant's value or a Data Layer variable's name), which tells the agent the config is readable from the output. It stops short of describing pagination or access 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?

Front-loaded with the action and result shape, followed by a short pointer for arguments; nothing is wasted. The type-code examples add length but earn their place by disambiguating variable types.

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?

The tool is a simple read with an output schema available, and the description still explains what the returned config looks like. The only real gap is parameter format guidance, which is more a schema deficiency than a description one.

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%, so the two parameters (container, workspace) carry no semantics from the schema and the burden falls on the description. It only cross-references list_gtm_tags without saying whether these are IDs or names, or what the empty-string default implies, so the compensation is minimal.

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 ('Lists the user-defined VARIABLES in a workspace') and enumerates the fields returned (name, variableId, type) with concrete type-code examples. This clearly separates it from nearby siblings like list_gtm_tags and list_gtm_triggers.

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?

Routes the agent to list_gtm_tags to resolve the workspace/container arguments, which establishes a useful prerequisite and ordering. It does not state any when-not condition or alternative listing tool, so it falls short of a full when/when-not answer.

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