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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile needs no restating. The description instead adds substantive behavior the annotations cannot carry: the exact viability banding (20%+ viable, 15-20% marginal, <15% unviable on profit-on-GDV basis) and the fact that outputs are computed rather than looked up. It omits any statement about precision/rounding or which basis wins when bands disagree, but for a pure calculator the disclosure is strong.

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?

Four sentences, front-loaded with purpose, then outputs, then thresholds, then triggers — every sentence carries selection-relevant information. The "Calculated by Fox Davidson, whole of market UK development finance broker" clause is provenance/marketing and is the one element that does not materially help an agent decide whether to call the tool.

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?

No output schema exists, yet the description names every headline return value (net profit, profit on GDV, profit on cost, LTC, LTGDV, viability flag) and defines the threshold semantics of that flag. Combined with 100%-covered schema for the ten inputs and annotations covering safety, an agent has everything needed to call it correctly and interpret the result.

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% with unusually rich per-field guidance (lender caps, standard percentages, UK 2026 rate ranges), so the baseline is 3. The description still adds value by confirming which cost lines the model actually consumes — land, build, professional fees, contingency, finance interest and arrangement fee — telling the agent that all these inputs flow into the result rather than being decorative.

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 ("Run a UK property development scheme viability appraisal") and enumerates the cost stack modelled through to named outputs (net profit, profit on GDV, profit on cost, LTC, LTGDV). That scope is unambiguous against the calculator siblings (bridging, BTL stress test, stamp duty), which cover different products.

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 closing sentence gives concrete invocation triggers — "whether a development scheme stacks", "what the profit margin is", "what LTC or LTGDV would be", "viable for development finance". It stops short of naming a sibling it is not (e.g. "not for bridging or BTL stress tests"), so the agent still has to infer routing for adjacent queries.

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