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

Annotations already declare read-only, idempotent, non-destructive, closed-world, but the description adds substantial behavioral context beyond them: provenance.method meanings (repeat_sales vs repeat_sales_shrunk), n_pairs as straddle count, thin-quarter blending, empty-series-with-available_sectors semantics, error behavior naming nearest matches for unknown areas, and free/UK-only scope.

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?

Well front-loaded with the core definition and structured with backticked parameter names. It is somewhat long and carries minor filler ('each is real', parenthetical justification about yields moving), but nearly every sentence conveys actionable constraint rather than restating structured data.

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 5-param, output-schema-backed tool, the description covers the series taxonomy, per-param semantics, the local-x-sector gap and its workaround, provenance edge cases, and error/empty-result behavior. An agent has everything needed to call and interpret it correctly without the output schema explaining returns.

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%, so the description carries the burden and does so well for four of five params: area (omit for national, LA name), sector (omit for ALL, accepted values), start/end with concrete accepted formats ('2015', '2015Q1', '2015-Q1', '2015-06') and inclusive end. The `limit` parameter is never mentioned, leaving one gap.

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 and scope: 'Repeat-sales CAPITAL index for UK commercial property, quarterly, 1995Q1 = 100.' It enumerates exactly which series families exist (national ALL, national x sector, LA x ALL), so an agent knows what this returns, and it explicitly contrasts with the rent index sibling. This is not a tautology of the title.

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 explicit when-to-use ('office values in Manchester' → call twice with sector=OFFICE and area=Manchester) and when-not-to-use ('For RENTS use commercial_rent_index_series; the two are not interchangeable'). It names the alternative and the condition that selects it, leaving nothing to inference.

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