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

Annotations already declare read-only, idempotent, non-destructive and closed-world, but the description adds critical behavior beyond them: cost of 5 credits (5p), coverage limited to the 33 London boroughs, `not_covered` outside London is not charged, and designation flags are three-valued (`applies` vs `unchecked`). This level of pricing and coverage transparency is exactly what an agent needs before calling.

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 core purpose and then layered with match_level, summary, coverage and cost — every clause carries information. It reads as a dense run-on paragraph rather than a structured list, which slightly hurts scanability, but there is minimal waste.

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?

Given a single-parameter tool with an output schema present, the description still explains result semantics (match_level values, summary buckets, coverage status, three-valued designations), pricing, geographic limits and the UPRN acquisition path. Nothing an agent needs to invoke it correctly 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 0% with a single bare `uprn` integer parameter, so the description must compensate — and it does, explaining the tool is keyed on a UPRN (not an address) and how to obtain one via address_autocomplete/address_resolve. It still doesn't state format constraints (e.g., integer, 12-digit) but the usage guidance is meaningful.

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 verb and resource ('Planning history AT this property'), then enumerates what is returned (applications linked to unit/building with decision, dates, appeal, CIL, match_level) and the summary/designations/LPA/coverage components. An agent can distinguish it from planning_applications, planning_check and property_history without checking schemas.

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?

States geography (UK only), keying requirement (UPRN, not address) and an explicit prerequisite workflow: call address_autocomplete (free) to narrow, then address_resolve to obtain the UPRN. Also clarifies that `not_covered` outside London differs from `no_applications` and is not charged. Lacks a direct comparison to sibling tools like planning_applications or property_planning_history_batch, but covers most when-to-use context.

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