list_dimension_values

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

No annotations are provided, so the description carries the full burden. It discloses that values only appear for activity periods, mentions the exclusive end default, and notes the metric argument does not compute the metric. However, it does not explicitly state whether this is a read-only operation or discuss rate limits or pagination. Given the absence of annotations, this is reasonably transparent but leaves a small gap about operation safety.

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 concise, front-loaded with a clear purpose, and uses short paragraphs for separate concerns (pre-filter usage, missing values, metric argument). Every sentence adds value without repeating schema details or annotations, achieving high information density in a compact form.

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 (10 parameters, no output schema, no annotations), the description covers key behavioral defaults (endTime exclusivity, granularity None for aggregates) and usage guidance. It lacks a brief description of return value shape (e.g., a map of dimension to values), but since there's no output schema, a note on what the response contains might be expected. However, the description focuses on discovery and filtering, and the schema covers parameter semantics well, making this only slightly incomplete.

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 important context beyond property descriptions: it explains the metric argument's role, the need for granularity to be omitted for limit, and the behavior of endTime. For instance, it clarifies the limit needs granularity omitted, which is not obvious from the schema. The description compensates for the schema's minimal context by tying parameters to usage patterns, even though it doesn't detail every parameter like startTime's relative formats (which the schema already covers).

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 states it lists actual dimension values (countries, product IDs, etc.) over a date range, which is a specific verb plus resource. It also distinguishes itself from siblings like list_dimensions (list dimension names vs. values) and from query/breakdown tools by framing it as a pre-filter discovery step.

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 advises running this before filtering, warns that filters match exact raw values, and recommends widening the date range if expected values are missing. It also clarifies that the metric argument is for namespace selection, not computation, which prevents misuse. Sibling tools like list_dimensions are implicitly contrasted by the 'actual values' phrasing.

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