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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so safety is covered. The description adds real behavioral context beyond that: the calculation is an approximation that ignores contribution caps and thresholds, and the fee can come from a published provider rate or a user-supplied quote. It stops short of describing any output structure or edge behavior.

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?

Two sentences, front-loaded with the core computation and followed by the essential accuracy caveat. No filler; every clause (cost components, fee source, cap caveat) earns its place.

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 read-only estimation tool with a fully-described schema and no output schema, the description conveys the return shape ('annual and monthly cost') and the accuracy limits. Nearly complete; only the absence of any pointer to related comparison tools leaves a small gap.

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 all six parameters are already documented. The description's mention of 'a provider's published fee, or one you supply from a quote' mirrors the schema's own override note for provider/monthly_fee_usd, adding little beyond what the schema states. Baseline 3 applies.

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?

Specific verb+resource ('estimate the annual and monthly cost of employing people in a country through an EOR') with an explicit breakdown of the computed components (gross salary, employer contribution, EOR fee, other monthly costs). It distinguishes itself functionally from get_country_employment_costs by including the EOR fee, though it never names a sibling tool 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?

The caveat 'A budget illustration, not a payroll quote: contribution caps and thresholds are not applied' tells the agent when this tool's output is appropriate and when it is not suitable for exact payroll. It does not, however, point to an alternative tool (e.g. compare_eor_providers) for the scenarios it excludes.

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