ons_geo_by_postcode

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

Annotations already declare readOnlyHint=true and idempotentHint=true, covering the safety profile. The description adds genuine value by disclosing that results come from a cache (so may be stale rather than live) and that multiple geographies may be returned ('all cached geographies'). It does not disclose cache-miss behavior or staleness policy, but for a read-only tool with strong annotations, the added context is adequate though not rich.

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?

A single 17-word sentence that front-loads the verb and resource, then attaches the parameter context. Every word earns its place and there is zero filler or repetition of schema content.

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?

The output schema covers return structure, so the description doesn't need to explain results. For a read-only, idempotent lookup with an output schema, the core is covered. But an agent still lacks guidance on includeRaw's behavior, postcode formatting, and what happens when a postcode has no cached data — gaps that matter for correct first-time invocation. Adequate but with clear holes.

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 of explaining parameters. It meaningfully explains derivationMode by mapping 'exact' to ONSPD and 'best_fit' to NSPL. However, includeRaw is never explained (what does 'raw' mean here?) and postcode format expectations (case, spacing) are absent. Partial compensation at best, with two of three functional parameters left to inference.

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 ('Lookup') and resource ('all cached geographies for a postcode'), which clearly states what the tool does. The 'cached' qualifier helps distinguish it from live-data siblings like os_places_by_postcode, and the by-postcode scope distinguishes it from ons_geo_by_uprn. However, it doesn't explicitly name a sibling to rule out, so differentiation is implicit rather than stated.

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 offers no guidance on when to choose this tool over alternatives. It explains the internal derivation modes (exact via ONSPD, best_fit via NSPL) but never addresses when to use ons_geo_by_postcode versus ons_geo_by_uprn, os_places_by_postcode, or ons_geo_area_summary. No exclusions or alternative-routing conditions are provided.

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