get_statistics

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

Annotations cover safety (readOnlyHint, openWorldHint), and the description adds real behavioral context beyond them: default fallback behavior, the closed-table successor handling with hints, and the expression syntax accepted. It does not discuss rate limits or payload size, but for a read-only query tool this is substantive added value.

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 core behavior and defaults are front-loaded, and the expression list and two examples each earn their place by disambiguating syntax that the schema only names. It is on the long side, but no sentence is pure filler.

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 3-parameter tool with an output schema, the description covers the ambiguous parts: default selection, expression grammar, and closed-table fallback. Return format is rightly left to the output schema, though lang's effect on results is never mentioned.

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 coverage is 67%, and the description meaningfully compensates by documenting the selection mapping format ('variable code -> value-code lists') and the allowed expressions from(...)/top(n)/*. Both worked examples tie table_id and selection to concrete outputs, which the schema alone does not convey; only lang is left without added explanation.

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 ('Fetch numbers from an SSB table as a compact CSV table') and immediately frames the tool around retrieval plus selection, which separates it from search_statistics and get_table_info. An agent can tell what it does 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?

Explains the default path when no selection is given ('totals ... and the last 12 periods, good for recent trend questions') and the alternate path when breakdowns are needed, including the dependency on get_table_info for variable codes. It does not explicitly contrast the tool with search_statistics, so it falls short of naming alternatives, but context is clear.

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