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

Beyond readOnlyHint/openWorldHint, the description discloses a rich behavioral contract that annotations cannot: ambiguous names return candidates instead of guessing, `locked` means Pro-gated not missing, nulls mean suppression or non-publication (never zero), a null percentile means it couldn't be computed, and ratios[].areaValue is null when the denominator is under 30. This is exactly the disclosure that prevents an agent from misreporting absent data.

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-loaded with purpose and metrics, then resolution behavior, then return-shape and null-handling semantics. Appropriate for a data-dense statistical tool. The final sentence on nulls/percentiles/ratios is long but each clause earns its place by preventing a specific misreporting error.

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 single-place statistics tool with no output schema, the description adequately covers what is returned (headline set, ratios[], percentiles, locked/Pro fields), how ambiguity is handled, and how to read nulls. Given no output schema exists, this description does the heavy lifting and nothing an agent needs to interpret results correctly 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 coverage is 100%, so the baseline is 3, but the description adds real semantics: name-or-code resolution behavior, the ambiguity-candidate return, the default-headline-set behavior that explains the `variables` parameter, and the Pro caveat on composite scores. It doesn't restate enum or year semantics, but supplements meaningfully.

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+resource ('current statistics for one Finnish postal area or municipality') and enumerates the exact metric domains returned. An agent can distinguish it from siblings like compare_areas, rank_areas, or get_area_report without opening any 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 example questions that select this tool, explains name-vs-code resolution, and points to list_variables for variable codes and variables/includeAllVariables for fetching specific data. It doesn't explicitly contrast against sibling tools like get_area_report or get_place_history, so exclusions are implied rather than stated.

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