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

Goes well beyond the annotations with cost (25 credits / 25p), geography (UK only), keying (UPRN not address), and — most importantly — the `sections_degraded` contract explaining that a failed section degrades in place and reports the kind of absence (`not_found`, `no_certificate`, `not_available`, `error`), each with different implications. It also guarantees parity with the standalone tools' receipts. That is materially actionable behavior an agent cannot infer from readOnly/idempotent hints.

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?

Well front-loaded: what it is and what it contains come first, then the operational warning, then the practical constraints. The capitalized `sections_degraded` warning is appropriately prominent. Minor redundancy between 'cheaper than the sections bought separately' and 'Costs 25 credits (25p)', but nothing that misleads.

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?

For a multi-section aggregate with an output schema (so return shape needn't be explained), the description covers cost, region, the identifier requirement, the degraded-section semantics, and fidelity to standalone tools. The only real hole is the undocumented `include_precedents` flag, which could change what the agent gets back.

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 must compensate. It does explain `uprn` well — integer identifier, not an address, with the sequence to obtain it — but `include_precedents` (default true) is never mentioned in either the schema or the description, leaving one of two parameters undocumented.

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 resource (one property) and a specific action (compose everything into one document), then enumerates the composed sections — summary, lease, risk report, rental estimate, energy, planning. It explicitly distinguishes itself from buying the sections separately, so an agent can tell it apart from property_summary, property_lease, property_risk_report and the other same-named siblings.

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 chain: this is keyed on a UPRN, so call `address_autocomplete` (free) to narrow and `address_resolve` to obtain one. It also frames the trade-off versus the standalone section tools on price. What's missing is an explicit statement of when NOT to use the bundle (e.g. when only one section is needed), though that is strongly implied by the per-section pricing note.

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