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

Goes well beyond the safety annotations (readOnly, idempotent, closed-world) with behavior the agent could not otherwise know: rows are grouped by ADDRESS not UPRN because flat-level UPRN collapses units, the returned uprn may name a neighbouring unit, and max_guide_to_avm EXCLUDES lots with missing guide/AVM. These disclose non-obvious counting and filtering semantics and the UK-only, free 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?

Front-loaded with the headline and the headline constraint, then the interpretation ladder as a scannable bullet list. The opening line 'both on the public record' is slightly rhetorical and the guide-section is long, but every block carries decision-relevant content rather than filler.

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 no prose, and the description covers counting unit, geography, and the exclusion trap. The remaining gap is the undocumented pagination/scope parameters (limit, offset, years), which an agent must guess at defaults for.

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 full burden. It explains max_guide_to_avm (with a worked 0.8 example) and pins geography to postcode_area/postcode_district rather than area_id, but leave limit, offset, years, min_auctions and is_commercial undocumented — five of eight parameters have no semantics anywhere.

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 and resource with scope: 'Properties that keep going to auction and NEVER SELL — the distress screen.' This is clearly distinguishable from siblings like auction_lots (all lots) and auction_discount (price fall), and the ranking logic ('failed auctions, then time on circuit') further pins down what the tool returns.

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?

Strong domain guidance: read guide_to_avm first, and an explicit interpretation ladder (above 1.0 = repricing conversation, 0.5-1.0 = worth a call, below ~0.5 = check the lease) that tells the agent both when the output is actionable and when it is a trap. It does not, however, name sibling tools or say when a different auction tool would be the better pick, so routing to alternatives is left to inference.

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