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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuine behavioral context beyond that: it returns result rows in the page language, raw engine outputs, sources with lastChecked dates, and a disclaimer, plus the rules year (2026) and last-updated date, which signals data staleness risk.

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 core calculation is front-loaded in one dense but readable sentence, followed by compact metadata (rules year, last updated, page URL, return shape). The nested cap clause ('multiples of the unskilled social minimum wage that step down over the benefit period') is slightly run-on, but there is little waste overall.

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?

For a two-parameter calculation tool with no output schema, the description covers the formula, the rules vintage, and the return shape (result rows, raw engine outputs, sources, disclaimer). What is missing is any eligibility/prerequisite context or guidance on interpreting the raw engine outputs, but the essentials for correct invocation are present.

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 the two parameters (salaireBrutMoyen and the enfantACharge enum with its default) are already fully documented. The description only reinforces the 85% linkage for a dependent child, which the enum description already states, and its one parameter-related sentence is generic boilerplate. Baseline 3 applies when the schema does the heavy lifting.

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 states precisely what is computed (Luxembourg ADEM full unemployment benefit with 2026 rules) and even summarizes the algorithm: 80% of the average gross salary of the last three months, 85% with a dependent child, capped by stepped multiples of the unskilled social minimum wage. The country and ADEM scope effectively separate it from siblings like greece_unemployment_benefit, though no sibling is named explicitly.

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?

There is no guidance on when to use this tool versus the other country calculators, no stated prerequisites (e.g. eligibility conditions, employment history), and no exclusions. The only usage-adjacent sentence ('Inputs marked "Only used when" are needed only in that case') is generic boilerplate that does not correspond to any 'Only used when' marking in the actual schema.

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