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

Annotations already cover readOnly/idempotent/non-destructive/openWorld=false, yet the description adds genuinely new operational facts: a 5-credit cost, no charge outside London, London-only coverage today, and the distinction between status: not_covered and no_applications. It also discloses the three-valued designation flag semantics and match_level values — context the annotations cannot carry.

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 before branching into coverage, cost, and keying caveats. The em-dash and nested-parenthesis structure makes it dense rather than wasteful, though the long first sentence packs several distinct concepts together.

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?

With an output schema present, return values need not be restated, and the description still supplies the interpretive context an agent needs: match_level levels, coverage semantics, three-valued flags, credit pricing, and the UPRN acquisition path.

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% on a single integer param, so the description must compensate — and it does, specifying that input is a UPRN (not an address) and how to source one via address_autocomplete/address_resolve. It stops short of stating the expected numeric format/range, but the semantic burden is largely met.

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 — planning history AT a property, comprising applications linked to the unit or its building — and enumerates the payload (decision, dates, appeal, CIL liability, development type). An agent can distinguish this from siblings like planning_applications and planning_check from the description alone.

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?

Gives an explicit prerequisite workflow: call address_autocomplete (free) to narrow, then address_resolve to obtain the UPRN, and warns that UPRN, not address, is the key. It also frames the coverage condition (London-only) so the agent knows the result semantics before invoking.

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