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

Annotations only declare readOnlyHint=true and openWorldHint=false, so the description carries the rest. It adds real behavioral context: the tax depends on regime and activity, a minimum tax may override the computed rate, the answer includes limitations that must be read before quoting, and it is an estimate from public texts rather than tax or legal advice.

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?

A single dense paragraph, but it is front-loaded with the answer-producing verb and resource, then layers regime/activity dependence, return fields, and the limitations/advice caveat. Every clause carries information; the delivery is slightly run-on rather than wasteful.

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, so the description steps in and enumerates the returned components (inputs, base, rate, minimum-applied flag, result, limitations), which is enough for an agent to consume the response. Coverage is strong for a read-only estimate tool; error modes like country_not_available are documented in the parameters rather than the description.

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%, so baseline is 3, but the description adds cross-parameter semantics the schema does not: 'activity' is required with the general regime and ignored with ae, and the rate depends on both regime and activity. Turnover base and the minimum-tax interaction are also clarified.

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 (Estimate) and a precisely scoped resource (IFU flat tax of Algerian micro-businesses, for 2026) plus the formula it mimics. An agent can tell it apart from siblings like get_tax_rates or calculate_casnos by scope, though the description never names an alternative directly.

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?

Usage is implied through the mention of the UpGrowth calculator and the instruction to read data.limitations before quoting, but there is no explicit when-to-use versus when-not, nor a named sibling alternative for the tax-rate lookup case.

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