describe_metric

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

With no annotations provided, the description must disclose behavior itself. It mentions that unsupported inputs cause an opaque 400 and burn query budget—useful behavioral insight. It doesn't explicitly state it's read-only, but that's implied by 'full definition' and the absence of mutation language. It could add details about response shape, but it's adequate.

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?

Two sentences, each earning its place: the first defines the tool's purpose and output details; the second provides actionable usage guidance. No redundancy, clearly structured, and front-loaded with the core definition.

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 single-parameter, no-output-schema metadata tool, the description covers what the tool does, what it returns, when to use it, and the risk of misuse. It lacks an explicit output schema description, but given the tool's nature, the description is sufficient and thorough.

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?

The schema already fully describes the 'metrics' parameter ('Exact, case-sensitive metric names, e.g. ['DailyActiveUsers']'). The description adds context about usage ('one or more metrics') but not new parameter semantics beyond what the schema provides. Since schema coverage is 100%, a baseline score of 3 is appropriate.

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 uses a specific verb ('describe') and clearly states the resource ('one or more metrics') and what it returns: display label, category, granularities, retention days, and valid dimensions. This distinctly differentiates it from siblings like list_metrics (which likely lists names only) and query_metric (which returns data).

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?

Explicitly instructs to 'Check this before querying an unfamiliar metric' and warns of consequences (opaque 400 error and waste of query budget) for using unsupported granularity/dimension. This gives a clear when-to-use directive and implies when not to use (when you already know the metric details).

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