get_metric

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

With no annotations, the description carries full burden: it does disclose the return payload (rows, the SQL used, caveats), which is genuinely useful context for trusting results. It says nothing about whether the call is read-only, what permissions or validation apply, or what happens when a metric name is unknown.

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 short sentences, front-loaded with the core action and followed by the return contract. No filler, though the grouping behavior could be folded in without bloat.

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 return shape in lieu of an output schema, which is good, and it is adequate for the required 'name' parameter. However, the optional grouping parameter and the distinctness from run_query remain unexplained, leaving meaningful gaps for a two-parameter analysis tool with no annotations.

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 both parameters need the description to compensate. It implies 'name' is a metric identifier defined in metrics.yml, which adds real meaning, but 'group_by' is never mentioned — an agent must guess its accepted values and effect on output shape.

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?

Specific verb + resource: 'Compute a governed metric from semantic/metrics.yml', plus a claim about what comes back. This distinguishes it reasonably from generic siblings like run_query or list_metrics, though it never names them explicitly.

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 phrase 'governed metric from semantic/metrics.yml' implies this is the path when an approved metric definition exists rather than ad-hoc SQL, and the sibling list (run_query, list_metrics) makes the contrast inferable. But no explicit when/when-not or prerequisite (e.g., call list_metrics first to find a valid name) is stated.

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