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

Annotations already declare non-readOnly, non-destructive and non-idempotent, and the description adds real value on top: the mutation is purely additive ('changes nothing existing') and takes effect in reporting 'from now on'. It does not cover GA4's custom-metric quota limits or the fact that the definition is not retroactive for past events, which would be worth one more line.

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, front-loaded with the action and its safety profile, with no filler. The trailing 'Tools revision: d80f65c0.' is build metadata that earns no place in a tool description.

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 output schema means return values need no explanation, and the additive/non-destructive behavior is well covered. But for a 5-parameter mutation with zero schema coverage, the description leaves the agent guessing on field values and on GA4-specific constraints, so it is adequate rather than complete.

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% and the description only glancingly gestures at parameter_name ('the parameter it names'). It says nothing about property, display_name, or the two defaulted fields scope (EVENT) and measurement_unit (STANDARD/CURRENCY), whose valid values and consequences are entirely undocumented in both the schema and the description.

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 custom metric on a GA4 property') and immediately scopes the effect: 'It adds one custom metric and changes nothing existing.' That clause implicitly separates it from ga4_update_custom_metric and ga4_list_custom_metrics, so an agent can distinguish create from update/list without opening a 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?

Usage is implied rather than stated: you create a metric when you want a new one, and the description notes it applies 'for events that send the parameter it names', which hints at prerequisites. But there is no explicit when-to-use/when-not guidance versus ga4_create_custom_dimension or ga4_update_custom_metric, and no mention of required permissions or per-property custom-metric limits.

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