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

With no annotations, the description carries the full burden and does so thoroughly: NULLs are skipped and NULL means SUPPRESSED not zero, aggregation_scope discloses source-published vs recomputed grains, a non_additive block and non_additive_sum advisory are emitted, coverage diagnostics expose suppression, and identifiers are contract-allowlisted (no raw SQL). This is well beyond what the schema conveys.

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?

Front-loads the core purpose before diving into agg/metric/group_by semantics, and every clause is substantive rather than filler. It is dense with stacked parentheticals, so a small readability cost, but no sentence is wasted.

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?

An output schema exists, so return values need not be described, yet the description usefully doubles down on return shape and suppression caveats. For a 14-parameter tool at 0% schema coverage it is nearly complete, with only offset and main_topic left unexplained.

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% across 14 parameters, so the description must compensate, and it largely does: it enumerates valid agg values, explains metric's key_metric default and its count behavior, defines group_by column types, maps filters/year/year_min-year_max/detail to query_dataset, and describes order_by/order plus top-N semantics. offset and main_topic (odd default 'education') are never mentioned, leaving two parameters undocumented.

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?

States a specific verb and resource ('Compute a grouped aggregate over one topic') and positions itself as 'the aggregation-first path', which distinguishes it from the row-returning sibling query_dataset. An agent can tell what this does and which path it represents without opening the schema.

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?

Gives real routing guidance: prefer weighted_rate over avg for a rate across multiple places/years, prefer source-published grains, and group_by the column (or use the published total row) instead of summing a non_additive column. It also names the describe_dataset/query_dataset adjacents. It stops short of an explicit 'use this instead of query_dataset when...' exclusion statement.

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