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

Beyond the readOnly/idempotent annotations, the description discloses unusually rich behavior: units follow the metric (per 1,000 residents, GBP/m2), confidence semantics (high only for observed, not modelled values), a fallback mechanism with quality='fallback' and carrierGeographyId for wider-published metrics, and that period is ignored for the find_areas factors. These are exactly the non-obvious traits an agent would otherwise get wrong.

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 value proposition is front-loaded in the first clause and nearly every sentence carries distinct information (units, confidence, fallback, default period, find_areas caveat). It is a single dense paragraph, though, so the fallback and find_areas caveats are buried mid-block rather than separated, which slightly hurts scanability.

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?

This is a complex tool with fallback geography logic, modelled-vs-observed confidence, and multi-month evidence rows, and the description covers all of those along with units and period defaults. An output schema exists, yet the description's return-format detail serves the purpose statement rather than duplicating schema burden; nothing essential to a correct call is missing.

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 100%, so the baseline is 3; the description earns an extra point by adding meaning not in the schema, namely that period is ignored for the find_areas factor metrics and that fallback geography can override the requested area. The area_id and metric_id semantics are already fully covered by the schema, so no further credit there.

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 states a specific verb and resource ('Evidence-backed value of one metric for one area in one month') and immediately enumerates what the value includes (regional/England percentiles, quality, sample size, category breakdown, up to 12 prior months). This scope ('one metric, one area, one month') distinguishes it implicitly from ranking tools like rank_areas_by_metric and aggregate tools like get_area_overview, and the find_areas cross-reference further separates its role.

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 clear usage conditions: period defaults to the metric's latest, and it explicitly describes how the find_areas factors (disorder, epc-share, leasehold-share, schools) are read via this tool 'to verify or explain a find_areas result'. What is missing is an explicit exclusion or named alternative for the other siblings (e.g., when to prefer get_area_overview or rank_areas_by_metric instead).

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