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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds substantial context beyond them: cost (30 credits/30p), geographic restriction, and interpretive caveats about backfilled floor areas, EPC room counts, anomaly flags, combined-unit demises, and correlated repeat sales. It also directs the agent to report selection/rejection reasons rather than silently dropping contrary sales, which is real behavioral guidance.

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 content is dense and largely relevant, but the invocation-critical facts (UK only, 30 credits, UPRN keying, address chain) are buried at the end after a long block of analysis caveats. Front-loading the operational essentials would make selection faster.

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 an output schema present, return values need not be explained, and the description covers scope, cost, prerequisites, and interpretation pitfalls well. The only material gap is the undocumented max_backfills parameter and no signal of result volume or how comps are selected.

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 must carry the load. It explains that the key is a UPRN (and how to obtain one), which meaningfully disambiguates the required parameter, but the second parameter max_backfills is never mentioned and its semantics (what a backfill is, why the default is 12) remain opaque.

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?

Opens with a specific resource and scope: 'Comparable sales in the same building or block', and clarifies it is keyed on a UPRN rather than an address. It does not explicitly contrast itself with near-siblings such as valuation_comparables, auction_comps, or comps_adjustments, so the agent must infer the boundary from the name 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?

Gives concrete preconditions: UK only, costs 30 credits, and an explicit prerequisite chain ('call address_autocomplete (free) to narrow, then address_resolve to get one'). It does not state when to prefer this over valuation_comparables or auction_comps, but the operational guidance is clear and actionable.

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