list_dimensions

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the filtering logic for multiple metrics (only dimensions valid for all) and the rationale ('because MetricFlow will refuse a group-by that has no join path to one of the metrics'). It also clarifies the output format (entity__dimension) and its direct compatibility with query_metrics. This is solid behavioral context, though it does not cover error handling, limits, or edge cases, so a 4 is appropriate.

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 front-loaded with the purpose, then moves to parameter details and behavioral notes. It is concise at roughly 100 words, and each sentence adds value—explaining the union semantics, the 'honest answer' rationale, and the output format. It could be slightly tighter, but the structure is logical and efficient, earning a 4.

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 description covers the input parameter behavior, the filtering semantics, and the output format, and it ties the output to query_metrics expectations. Since an output schema exists, return-value details are presumably documented there. The description is complete for a read-only discovery tool, though it could mention potential empty results or error conditions. This is slightly above average, so a 4.

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 fully explain the parameter. It does so clearly: 'metrics: One or more metric names, comma-separated' and explains the behavior when multiple are given. Since there is only one parameter and it is thoroughly documented, the description fully compensates for the schema's lack of parameter descriptions.

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 clear, specific statement: 'List the dimensions a given set of metrics can legitimately be grouped by.' This identifies the verb, resource, and scope precisely. It also distinguishes itself from sibling tools by referencing the exact form expected by query_metrics, making its purpose unmistakable even without naming alternatives.

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 provides useful context about behavior when multiple metrics are given (only dimensions valid for all), and notes the exact form needed by query_metrics, which implicitly guides when to use it. However, it does not explicitly state when to use this tool over alternatives like list_metrics or describe_metric, nor does it mention exclusion conditions. The guidance is clear but lacks explicit 'use this instead of X' or 'when not to use' statements.

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