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

Annotations already declare readOnlyHint=false and destructiveHint=false, so mutation semantics are covered; the description instead contributes the non-obvious facts: property_id values outside the workspace are rejected, and propagation into reporting takes 24-48h. It also gives the exact query syntax in ga4_report, which is genuinely useful cross-tool behavioral context.

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 creation statement is front-loaded, then parameter notes, then the reporting caveat. The sentence about immediate ga4_report returning empty rows and the query format is long but carries high-value information, so it earns its place; only the property_id parenthetical is slightly redundant.

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 values need no explanation, and the description covers the two things an agent could get wrong: which property is allowed and why reports appear empty right after creation. The remaining gap is the undocumented display_name/parameter_name semantics on a 6-parameter creation tool.

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 description must carry the load. It explains scope (listing the values absent from the schema), property_id (workspace-constrained, rejected otherwise), and workspace (optional when only one exists), but leaves display_name, parameter_name, and description unexplained — including the required parameter_name, whose relationship to the query syntax is only indirectly implied.

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 opens with a specific verb and resource ('GA4 Custom Dimension anlegen') that unambiguously separates it from ga4_create_custom_metric and ga4_create_key_event. It does not explicitly name the sibling to avoid, but the compound noun 'Custom Dimension' makes the distinction self-evident.

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 names the allowed scope values (EVENT, USER, ITEM) and warns that reports will show empty rows for 24-48h, which tells the agent both how to use it and what to expect immediately after. What is missing is an explicit statement of when not to use it (e.g., custom metrics, audiences).

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