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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered; the description instead discloses the actual calculation methodology — the ownership-dependent stress rate rule (5.5% for personal, max(product, 5.5%) for ltd) and the three ICR thresholds applied. That is genuinely additive domain behavior, though it omits assumptions such as whether rent is gross-of-costs or how lender criteria are sourced beyond the broker attribution.

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 action and outputs, then methodology, then triggers — a sensible order with no filler sentences. The broker attribution line ('Calculated by Fox Davidson, whole of market UK property finance broker') is mildly promotional but does signal sourcing authority, so it only slightly dilutes an otherwise tight definition.

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?

There is no output schema, and the description compensates by enumerating every returned quantity (ICR at both rates, gross yield, max loan per threshold, lender categories). Combined with the ownership-aware stress rule, an agent has everything needed to call it and to describe the result to a user.

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 coverage is 100% and already documents all four parameters including the ownership stress-rate rule and the HMO/MUFB rent aggregation note, so the description's restatement of 'personal uses 5.5%, ltd uses max of product or 5.5%' adds little new information. Baseline 3 applies; the description does not extend parameter meaning beyond the schema (e.g., units, rounding, or edge behavior at the loan_amount minimum).

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 domain resource ('Run a UK buy-to-let ICR stress test') and enumerates exactly what it computes: ICR at product/stress rates, gross yield, max loan at 125/145/170% thresholds, and lender-category qualification. It is unmistakably distinct from the sibling calculators (bridging, stamp duty, development appraisal), so an agent can route correctly without opening a schema.

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 four concrete triggering questions ('does the deal stack', 'what is the ICR', 'max loan my rent supports', 'HMO/MUFB qualification'), which is strong positive routing guidance. It stops short of naming alternatives or stating when-not to use it, relying on the obvious domain separation from siblings to carry the rest.

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