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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds the scoping fact that it is French and that the return is an annual tax figure, but it does not disclose simplification limits — e.g. that real taxe foncière also includes departmental rates, the 50% abatement base, and management fees — which matters for a tax estimate.

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 short sentences, purpose and audience front-loaded, then inputs, then return, then a cross-reference. Nothing is padded, though the "Returns annual tax due" sentence is largely redundant given the output schema.

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?

Output schema exists so return values need no explanation, and both params are documented. What is missing is the accuracy scope (is this a rough estimate or the full statutory computation?) and disambiguation from calculate_property_tax_estimate_fr — an agent could easily pick the wrong sibling.

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 description coverage is 100%, with both parameters fully documented including the French term, units, default, and min/max bounds. The description only restates those same two inputs, so per the baseline rule a 3 is appropriate; it adds no format or interpretation detail beyond the schema.

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 verb and resource — computing French taxe foncière — and even glosses it in English as annual property tax. However, it never distinguishes itself from near-identical siblings such as calculate_property_tax_estimate_fr or calculate_us_property_tax, leaving the agent to guess which variant applies.

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?

"Use for owners of property in France" gives a usable context but no when-not-to-use guidance and no explicit choice among the several property-tax siblings. The list_bundles pointer is a helpful route for discovering related tools but is not an alternative-tool recommendation.

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