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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), so the bar is lower. The description adds genuine non-structured context: the forward-validated, leakage-free methodology, monthly refresh cadence, and crucially the `status: no_rows_yet` empty-state that must not be read as zero error. It stops short of describing auth or rate limits, but nothing contradicts the annotations.

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?

Purpose and the crucial empty-state caveat are front-loaded, with filters and scope ('UK only. Free.') packed into a compact trailing block. The prose is slightly ornate ('measured the only way that cannot leak') but nearly every clause carries real information; no wasted sentences.

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 read-only analytics tool with a full permission annotation set and an output schema, the description supplies what structured fields cannot: the metric definitions' meaning, the pre-October-2026 empty-state, geographic scope and cost. The only shortfall is the incomplete enumeration of asset_class values, which could mislead an agent into thinking 'Other'/'Unclassified' are invalid.

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 and largely delivers: it names all three filters and supplies formats/examples ('since' as YYYY-MM, 'model_version' e.g. gbm-h3-v4). One gap: it lists only Residential | Commercial | Mixed-Use for asset_class while the schema enum also allows 'Other' and 'Unclassified'.

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 verb+resource ('how accurate our valuations have been') and precisely defines the measurement (registered sales the model had already valued vs. actual price paid, reported as MdAPE/PPE20/n). It is unmistakably distinct from siblings like valuation_estimate, valuation_full and valuation_comparables, which produce valuations rather than score them.

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?

It gives a critical timing caveat ('until the first vintage lands in October 2026 the answer is no_rows_yet'), which tells the agent when the tool is and isn't useful. However, it never says when to reach for this versus other accuracy-adjacent siblings, and no exclusion or alternative is named.

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