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

Goes well beyond the annotations by documenting a validation path that fails locally without hitting the API ({'error': 'restricted_metric_types_required'}), the fixed EVENT scope restriction, and the property/workspace rejection rule. That is exactly the kind of failure-mode disclosure annotations (readOnly=false, destructive=false) cannot carry.

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, then constraints, then response shape – a sensible order. The long measurement_unit enumeration is costly but functional; a few lines are telegraphic rather than wasteful.

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 8-parameter mutating tool with annotations and an output schema, the description covers the highest-risk input (restricted_metric_types), scope limits, and tenancy rules. Remaining gaps – naming conventions for parameter_name, duplicate-name behavior, reversibility – are secondary since return values are covered by the output schema.

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 0% schema description coverage the description does real work: it enumerates allowed measurement_unit values, constrains scope to EVENT, defines the restricted_metric_types contents and its conditional requirement, and explains property_id and the optional workspace slug. It leaves parameter_name/display_name/description conventions unexplained, so not fully compensating.

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 opening line 'GA4 Custom Metric anlegen' states a specific verb + resource, which clearly separates it from siblings such as ga4_list_custom_metrics or ga4_archive_custom_metric. It does not explicitly name an alternative, but the resource specificity makes the intent unambiguous.

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?

Gives concrete preconditions: property_id must belong to the workspace (others rejected), scope may only be EVENT, and restricted_metric_types is mandatory for CURRENCY. It does not state when to prefer list/archive siblings over creating, but the usage context is clear enough to act on.

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