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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is settled. The description contributes real domain behaviour: retained and serviced cost the same while rolled-up costs more, and the MCOB 3A thresholds (GBP 300k income / GBP 3m net assets) lift the term cap from 12 to 60 months. It does not say anything about rounding, currency assumptions, or what happens when optional HNW inputs are omitted, so it is useful but 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?

Front-loaded with the core action and the list of computed outputs, then interest structures, then the MCOB rule, then usage triggers — a sensible ordering. The 'Calculated by Fox Davidson, whole of market UK mortgage brokers authorised and regulated by the FCA (FRN 1056214)' sentence is attribution rather than invocation guidance and slightly dilutes density.

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 16 parameters, no output schema, and a single required field, the description usefully enumerates the return values (total interest, fees, gross facility, net advance, LTV, annualised cost) so the agent knows what comes back. Combined with the low required-parameter count and fully documented schema, only minor gaps (default assumptions for rate, rate/term sourcing) remain.

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 100% across all 16 parameters, including the enum semantics for interest_structure and the MCOB 3A thresholds, so the schema does the heavy lifting. The description restates the three interest structures and the HNW check but adds no syntax, defaults, or interaction rules (e.g. how add_arrangement_fee_to_loan couples with exit_fee_on_gross) beyond what the schema already documents. Baseline 3 applies.

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 precise verb and resource ('Calculate the full cost of a UK bridging loan') and enumerates the concrete outputs (interest, arrangement/exit fees, gross facility, net advance, LTV, annualised cost), plus the MCOB 3A term check. An agent can tell this apart from btl_stress_tester or uk_stamp_duty_calculator, but the sibling `bridging_cost_analyser` is a near-neighbour that the description never mentions or differentiates against.

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 final sentence gives explicit triggering conditions: cost questions, interest structure questions, LTV, regulated vs unregulated, and maximum term on a regulated bridge. That is a clear, enumerated 'when to use', but it offers no exclusions and does not route the agent to or away from the overlapping `bridging_cost_analyser` sibling.

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