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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, non-destructive, openWorldHint=false), so the bar is lower. The description adds real behavioral context beyond them: the hard horizon ceiling of seven periods, the settled-index anchor, the method (smoothed repeat-sales index), and the explicit disclaimer that this is not a property valuation, which guards against misuse as an appraisal tool.

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 what is returned, then constraints and caveats; roughly 70 words with no filler sentences, and the terse 'UK only. Free.' is efficient. The phrase about the smoothed repeat-sales index is slightly ornamental but earns its place as a misuse guard. Minor redundancy between 'the horizon the index publishes' and 'nothing beyond it is offered'.

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?

An output schema exists, so return values need not be described, and the bands, anchor and horizon limit are all covered for a read-only forecast tool. The remaining shortfall is on the input side: with 0% schema coverage, the description should specify the area_code format and what monthly vs quarterly changes about the series. Otherwise an agent has everything needed to call the tool 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?

Schema description coverage is 0%, so the description carries the load. It partially compensates: 'postcode district or local authority' maps to the area_type enum, and 'up to seven forecast periods' documents the horizon cap, while 'publication grain' loosely gestures at frequency. It says nothing about the expected format of area_code (GSS code vs postcode) or the distinction between monthly and quarterly frequency, leaving two of four parameters ambiguous.

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+output shape: a published house-price index forecast for a postcode district or local authority, anchored on the last settled index point with up to seven banded periods. It also implicitly separates itself from valuation tools by noting the forecast is a projection of the smoothed repeat-sales index, not a property valuation. It never names the closest sibling (market_index_series / asking_price_index_series) explicitly, so it stops short of full sibling differentiation.

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?

The description states hard constraints — UK only, free, horizon capped at seven with nothing beyond offered — which effectively tells the agent when the tool is in scope. However, it gives no explicit guidance on when to prefer this over the historical index tools (market_index_series, asking_price_index_series) or what to do if a forecast is unavailable for an area. Usage is implied by 'forecast' rather than directed.

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