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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds substantial context beyond them: cost, UK-only scope, the meaning of status: no_lease, the fact the AVM does not adjust for short term, and the legal caveat that UPRN linkage does not verify the legal demise.

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 opening sentence front-loads what the tool returns, and every subsequent sentence carries real content (limitations, flags, cost, linking workflow). It is dense and long, but nothing reads as filler — only the volume of caveats keeps it from a 5.

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?

An output schema exists, yet the description still characterizes the return (longest-expiry record, alternatives, identifiers) and flags truncation/unavailable alternatives. Combined with cost, scope, and the no_lease semantics, an agent has everything needed to call and interpret it correctly.

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?

The single parameter has 0% schema description coverage, so the description carries the burden, and it does: it clarifies that uprn is a UPRN key rather than an address and points to address_resolve to obtain one. It stops short of stating the integer format explicitly, but the meaning is well conveyed.

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 — registered leases linked to a UPRN — and details exactly what comes back: the longest-expiry record plus up to ten alternatives with register descriptions and title/record identifiers. It is clearly distinguishable from siblings like property_lease_batch and ownership_by_title.

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 workflow: 'call address_autocomplete (free) to narrow, then address_resolve to get one,' and states the tool is keyed on a UPRN rather than an address. It also states UK-only scope and the 5-credit cost, so an agent knows when and how to reach for it.

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