breakdown_metric_by_segments

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

With no annotations provided, the description carries the burden of disclosing behavior. It clearly states that the tool performs a read operation, returns ranked segments per dimension, flags rate-like metrics at certain thresholds (1.5x/0.67x), and costs one query per dimension. It also discloses that endTime defaults to today's UTC midnight for complete buckets, which is beyond schema info.

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 well-structured and front-loaded: the first sentence states the core purpose, the second provides a use case, and the last adds cost guidance. No fluff, every sentence serves a purpose.

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?

Given the tool's complexity (8 parameters, nested filter objects) and lack of output schema, the description provides comprehensive context: it explains the main use case, performance considerations, and how parameters like dimensions and limitPerDimension behave. It also points to sibling tools for discovering dimension values. This is complete enough for an agent to use effectively.

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?

Although schema coverage is 100%, the description adds crucial semantic context: it explains that dimensions defaults to all supported dimensions, that limitPerDimension helps cap segments for high-cardinality fields like Country and ProductKey, and that filter values can be discovered via list_dimension_values. This goes beyond basic schema descriptions to explain how parameters interact and when to use them.

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 clearly specifies the action ('Slice one metric by every dimension it supports'), the resource (metric by dimensions), and the outcome (ranked segments within each dimension). It also differentiates from siblings like query_metric and query_metrics by emphasizing the multi-dimension, per-dimension ranking approach.

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?

The description explicitly states when to use this tool ('This is the fastest way to answer 'who is this bad for?') and contrasts it with alternatives like query_metric/query_metrics by highlighting that it surfaces segment issues without guessing dimensions. It also provides cost guidance ('Costs one query per dimension') and advises restricting dimensions to save resources.

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