dbtBigQuery

describe_metric

Get a metric's complete governed definition, including assumptions, trade-offs, failure modes, grain, and source measures, from the dbt semantic layer.

Instructions

Return the full governed definition of one metric.

Args:
    metric: The exact metric name, as returned by `list_metrics`.

Returns the definition, the assumption it rests on, the trade-off accepted
when it was chosen, what breaks if someone defines it differently, its
grain, and the measures or metrics it is computed from. This is the
authoritative text — it is read from the compiled dbt manifest, which is
generated from models/semantic/metrics.yml.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`metric`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Sep 21, 2026

TDQS

A4.5/5.0

Behavior4/5

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 the read-only nature implicitly with 'Return' and explicitly states the source: 'read from the compiled dbt manifest, which is generated from models/semantic/metrics.yml, and calls it 'authoritative text.' This goes beyond a simple operation statement, though it does not mention error handling or edge cases.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is tightly organized: purpose, argument, return contents, and source. Every sentence adds value—no filler or repetition. The key purpose is front-loaded, and the additional details are compactly grouped in the 'Returns' sentence.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple single-parameter tool with an output schema, the description is complete. It explains the input source, lists the return components (definition, assumption, trade-off, breakage, grain, measures/metrics), and clarifies the authoritative source. No essential information an agent needs to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0% description coverage for the 'metric' parameter, so the description must compensate. It does so by specifying 'The exact metric name, as returned by list_metrics,' which adds critical guidance about validity and source that the schema lacks. It could include format examples or case sensitivity, but the provided semantics are sufficient.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Return the full governed definition of one metric,' which names a specific verb, resource, and scope. It distinguishes this from siblings like list_metrics (which lists) and query_metrics (which queries data), leaving no ambiguity about what the tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context: the metric argument must be 'the exact metric name, as returned by list_metrics,' which tells the agent how to obtain a valid input. However, it does not explicitly state when to prefer this over alternatives like explain_metric_sql or query_metrics, so it lacks explicit exclusions.

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

Deploy Server