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

Annotations already declare the safe read-only, idempotent, non-destructive profile, so the burden is lighter. The description adds real behavioral value: it discloses the computation method, that it subtracts the filing fee when known, that it also shows the upward cost, and that it will not guess municipal rates.

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?

The trigger is front-loaded and every sentence carries information, though the parenthetical 'because a review can raise the value' and the closing instruction slightly pad an otherwise efficient passage.

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 reasonably describes what the tool returns (savings and upside cost) and the inputs it depends on. It is complete enough to call correctly, though it does not detail the output structure or units of the returned figures.

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 the baseline is 3, but the description adds meaning beyond the schema by clarifying that 'baisse' is a hypothetical chosen by the user rather than a predicted value, and that the tax rate must come from the user's tax bill.

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 names a specific quantitative job — multiplying a hypothetical assessment reduction by the tax rate over remaining roll years and subtracting the filing fee — which is distinct from siblings like frais_revision or taux_courants. An agent can tell exactly what resource and output this tool produces.

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?

It states the exact trigger ('when the user asks how much they could save on property taxes if their assessment went down, or whether contesting is worth the fee'), covering both the savings and cost-benefit use cases. It also specifies the prerequisite action of asking the user for their tax rate rather than guessing.

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