describe_metric

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

No annotations are provided, so the description carries the burden. It implies a read-only lookup (a definition, not an execution) and discloses what the payload contains, but says nothing about permissions, caching, or lookup failure behavior. Output schema covers the return shape, so this is the acceptable minimum.

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?

A single front-loaded sentence that states what the tool returns first and the consult trigger last. No filler, though the enumeration is slightly dense.

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?

With one documented parameter and an existing output schema, the description needs only to convey purpose and the consult trigger, which it does. An agent has enough to call it correctly; only clearer routing against query_metric is missing.

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 100% with a single well-named "metric" parameter ("Nome canônico da métrica"). The description adds no format or canonicalization guidance beyond that, so the baseline 3 applies.

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?

Starts with a specific verb+resource ("Definição completa de uma métrica") and enumerates the payload it delivers: expression, grain, dimensions, allowed filters, and usage notes. This clearly separates it from query_metric and list_metrics, though no sibling is named 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?

"Consulte antes de montar um recorte incomum" gives one loosely-stated situation to reach for this tool, but the conditions are vague (what counts as "incomum") and no alternative (e.g. query_metric) is referenced for the common case. The "quando usar/quando NÃO usar" phrasing describes output content, not tool-selection guidance.

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