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

The annotations already declare this a safe, idempotent, closed-world read, so the description is free to spend its words on behavior, and it does: it discloses which time windows are computed (latest whole year, plus incomplete current year against the same months a year earlier), that quartiles and sales accompany the median, and that floor-area pricing is conditional on the optional input. It does not discuss limits on the recency or completeness of the current-year figures, which would have been the last useful disclosure.

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?

One dense but well-ordered paragraph: the operation and its inputs come first, the computed outputs follow, and the property-type rationale closes it. Every clause carries information, though the single sentence running from 'latest whole year's' through 'a year earlier' is long enough that an agent must parse it carefully.

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?

There is no output schema, so the description must carry the return contract, and it does in detail — per-district median price per m², quartiles, sales counts, 2015-onward change, year-to-date comparison, and conditional floor-area cost. Combined with full schema coverage on the three inputs and annotations covering safety, an agent has everything needed to select and call this correctly.

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?

With 100% schema description coverage the baseline is 3, but the description adds real meaning beyond the field docs: 'two to six' is tied to the actual comparison semantics, and the property_type enum is explained as a controlled-constant rather than just a code, with an explicit rationale. The floor_area_m2 behavior (pricing that area at each district's median) is also spelled out, which is more than the schema's 'optional floor area to price at each district's median' conveys.

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?

The description names a specific operation (side-by-side comparison) on a specific resource (two to six postcode districts) and enumerates exactly what is computed: median price per m² with quartiles and sales, change since 2015, year-to-date versus the same months last year, and optional floor-area pricing. What keeps it from a 5 is sibling differentiation — it never says how it differs from compare_homes, district_statistics, or area_overview, so an agent must infer the boundary from the sibling names alone.

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: the tool is for comparing places, and the closing sentence explains why property type is pinned (comparing flats against houses compares the mix, not the place). That is a genuine usage constraint, but there is no explicit 'use this when...' and no named alternative, so the agent must derive the choice between this and district_statistics or compare_homes on its own.

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