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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it excels: NULL usually means SUPPRESSED not zero, bad filters return a self-describing error, NULL cells sort last, pages are small with max 500, and truncated responses point to a bulk_export endpoint. It also explains the columns descriptor array and key_metric echo, giving an agent a clear picture of what the call will do and what the response means. There is no contradiction with annotations because no annotations exist.

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 dense but every sentence earns its place. It opens with the core purpose, then flows through filters, year selection, grain, return shape, projection, sorting, pagination, and error behavior in a logical order. There is no filler, repetition, or vague phrasing.

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 13-parameter tool with no annotations, this description is remarkably complete. It covers return semantics, null semantics, sorting, pagination limits, bulk export, label joining, and error handling, and it points to describe_dataset for filter vocabulary. The presence of an output schema means it need not restate the full return shape, and the description still goes beyond that requirement.

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?

Although schema coverage is 100%, the description adds substantial meaning beyond the schema: filters is a dict of column to value/list-of-values with OR/AND semantics, year vs year_min/year_max are mutually exclusive, detail defaults to finest grain, columns projects a subset, and order_by sorts NULL-suppressed rows last. It also directs the agent to describe_dataset for the exact valid filter keys and enum values, which is exactly the kind of cross-tool semantic glue the schema cannot provide.

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 opens with a specific verb-resource pair: 'Query one topic's gold facts with dimension labels joined in.' It clearly distinguishes the tool's read/query role from siblings like aggregate, describe_dataset, and distinct_values, and states what comes back on each row. This is far above a tautology and gives an agent an accurate mental model immediately.

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 description gives strong in-tool usage rules: use year OR year_min/year_max never both, use order_by+order for server-side top-N, set include_labels=false for leaner pulls, and prefer bulk_export over pagination when truncated. It references describe_dataset for valid filter keys. It does not explicitly say 'use aggregate instead when you need aggregations' or otherwise compare against sibling tools, so it stops just short of a full 5.

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