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

Annotations already establish readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description goes further by enumerating what the calculation actually consumes — transfer duty and costs, holding costs, agent commission — and, with no output schema present, names the three returned figures, which is genuinely additive context.

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?

Two dense sentences: the first front-loads the deal type and the cost stack, the second delivers the returns. No filler, no restatement of the title, and the most decision-relevant output (max offer) lands last for emphasis.

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 7 parameters, no output schema and only minimal annotations, the description does enough work to make the tool callable: it names the cost components and the returned metrics. What's missing is the holding period semantics, the default assumptions (1% holding cost) and any caveat that transfer duty is a SA-specific calculation — relevant for an agent judging whether results are trustworthy.

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?

At 57% schema coverage the description meaningfully complements the schema: it ties target_margin_pct to the 'maximum sensible offer' output and clarifies that selling cost means agent commission and that holding costs are modelled over time. It doesn't explain the holding cost default of 1% of purchase price or what months_held governs, leaving one parameter effectively unaddressed.

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?

The description gives a specific verb+resource ('Checks a buy-renovate-sell deal') plus the exact analytical output (profit, margin, max offer), which clearly separates it from the estimation siblings. It stops short of naming estimate_works or estimate_new_build as the tools that feed it, so sibling differentiation is implied by domain rather than stated.

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 phrase 'buy-renovate-sell deal in South Africa' implies the scenario, and the required trio of inputs sketches a use case. But there is no explicit 'use this when...', no exclusion ('not for new builds — use estimate_new_build'), and no mention of scope limits such as single-property vs portfolio.

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