custom_metrics_write

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

Beyond the destructive annotation, the description discloses important behavioral consequences: changing a metric type can make old data inconsistent, and deleting stops tracking while preserving historical data. It also clarifies enum-specific creation 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?

The description is dense and front-loaded with the overall purpose before breaking down each action. Every sentence carries actionable information, with no filler.

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 destructive nested-object write tool with no output schema, the definition covers the critical create/update/delete semantics, required fields, and data-integrity caveats. Remaining details such as agentId and mode are either obvious from context or already documented in the 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?

Schema coverage is low at 40%, and the description compensates by mapping action values to required fields and by explaining the metric object structure. It does not explain agentId or mode, but mode is already described in the schema and agentId is strongly implied by 'on an agent'.

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 states a specific verb set and resource: create, edit, or delete a custom analytics metric on an agent. It clearly distinguishes this write tool from the sibling read tool by enumerating mutating actions rather than read behavior.

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 gives action-specific usage conditions: create needs key + type + description and enum options, update uses metricId plus only changed fields, and delete uses metricId. It does not explicitly route readers to custom_metrics_read or state when not to use this tool, so it stops short of the top score.

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