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

Annotations already establish the safe read-only, idempotent, closed-world profile, and the description adds real substance on top: the exact duty components included, the 2025 rate increase and first-time-buyer exemption, and the explicit exclusion of unregulated disbursements. It does not cover auth needs or return shape, but the scope disclosure is well beyond what the annotations carry.

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 country and the call trigger, then the computation basis and parameter modes. Dense and mostly earned, though the component enumeration in the middle sentence is long enough that it slightly buries the usage instruction.

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 no output schema, the description carries the return-value burden, and listing the computed components (duty, communal tax, collection fee, CSI, émoluments with VAT) effectively implies the breakdown. It stops short of saying whether a total is returned or how the estimate is presented.

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%, so baseline is 3, but the description adds cross-parameter semantics the schema does not: 'ancien' is the default and requires a département, while 'neuf' uses a reduced rate. That dependency and default behavior are genuinely useful additions.

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: computing the 'frais de notaire' (transfer duties + notary fees) for a French property purchase. The country scoping and the explicit list of computed components make it clearly distinct from siblings like taxe_mutation or closing_costs_us without opening either 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?

Gives a precise trigger ('Call this when the user wants the frais de notaire on a property purchase in France') and pins the market with 'FRANCE'. It does not name sibling alternatives or state when NOT to use it, so it stops short of the explicit routing a 5 requires.

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