query_metrics

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

No annotations are provided; the description covers the load-bearing behavior: per-query rate limiting, error-without-a-bort, and dropped unsupported operations. It doesn't document return envelopes or all failure modes.

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 two well-formed paragraphs, front-loaded with purpose and differentiating value, but is otherwise dense and reference-like; the structural weight sits on the schema.

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 tool has 9 parameters and a 100% populated schema, but lacks an output schema and does not account for success-return or response-shape. The rich text around rate limits, error fields, and overprocesses fills in most of the behavioral context.

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 fully covers the 9 parameters; the descriptions add defaults (endTime default to today's UTC midnight, exclude; startTime relative; granularity calendar semantics; lastN shorthand; universeId alias) and therefore go beyond lazy names.

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?

Description opens with 'Query several metrics over the same time range', a specific verb+object. It clearly distinguishes itself from query_metric by supporting multiple metrics, automatic query pacing, and partial failure rather than abort.

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 states 'prefer this over repeated query_metric calls', explains the 30-query/min API limit, and notes that unsupported filters/breakdowns are silently dropped. Lacks an explicit when-not-to-use, but the guidance is otherwise strong.

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