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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorldHint=false, so safety is covered; the description goes further by disclosing that `percent`-unit values are fractions (0.06 = 6%) and that unit-prefixed fields are only populated for ~13–54% of suburbs, meaning a unit filter silently won't match uncovered suburbs. Those are real behavioral caveats that change how a caller interprets results. It omits anything about the shape of the returned catalog beyond 'label and unit' and the stray '0c.' token is unexplained.

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 content is front-loaded and dense with useful detail, but the opening '0c.' is a stray artifact that reads as a truncation bug, and the closing '**Free.**' markdown tag is unpolished for a tool description. The line breaks inside sentences also break the prose mid-clause, slightly hurting scanability.

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?

With no parameters, no output schema and no nested objects, the description should carry the burden — and it largely does: it explains what the returned catalog contains (label + unit), how to interpret unit values, and the population caveat for unit fields. The only meaningful gap is that it never states the returned structure or how many fields to expect, which for a catalog tool would help an agent plan.

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?

Zero parameters, so the baseline is 4. The description still spends its space on semantics that matter downstream — the meaning of the `percent` unit, the distinction between `unit`-prefixed (apartment) and unprefixed (house) keys, and the fact that both can be combined in one query — which is exactly the interpretive context a field catalog needs.

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 resource clearly: a catalog of 'every field you can filter / sort on, with its label and unit,' which tells an agent this is a metadata reference, not a data query. It does not explicitly name the sibling tools (e.g. suburbs_finder_search) it exists to support, so the differentiation from the 30+ area_stats/finder siblings is only implied by the word 'catalog'.

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?

Usage is implied rather than stated: an agent can infer this is a discovery step before building a filter/sort query, but there is no explicit 'call this first' instruction, no exclusion of alternatives, and no mention of what to do with the returned fields. The house/unit note gives a hint about query construction but is not framed as guidance.

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