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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: rows return in requested order with no ranking, and the data is a snapshot dated 2026-10-01, which tells the agent about result freshness and output ordering.

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 clauses, each doing distinct work: scope, ordering, data vintage, and disclaimer. Nothing is padded and the most decision-relevant fact (what cost is computed) leads.

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 usefully covers what comes back (ordered rows) and the data vintage, and it flags the EOR-fee exclusion. Minor gaps remain around error behavior for invalid country codes, but nothing essential to correct invocation is missing.

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 50%, and the description's '2 to 10 countries' plus 'same gross salary' duplicate the bounds and semantics already encoded in the schema. It adds no format or edge-case detail (e.g., unknown country codes) beyond what the parameters declare, so the 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?

States a specific computation (statutory employer cost of the same gross salary across 2-10 countries) with an explicit scope bound ('before any EOR fee'), which implicitly separates it from cost siblings like total_hiring_cost. No sibling is named outright, so it falls short of a 5.

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 by the framing ('Cost comparison, not legal or tax advice') and the exclusion of EOR fees, but the description never says when to pick this over employer_cost or total_hiring_cost, nor states prerequisites. Adequate but leaves routing to inference.

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

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

Annotations already cover the safe-read profile (readOnlyHint, openWorldHint=false), and the description adds real context beyond them: a data snapshot date, the convention that floor/ceiling totals are rendered 'at least'/'at most', and an explicit not-legal-advice disclaimer. It stops short of describing failure modes or coverage limits (which countries, how stale).

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?

Dense but front-loaded: the core purpose, output shape, qualifier convention, snapshot date and disclaimer are ordered by importance. The single long sentence packs a lot, though the disclaimer and snapshot could be trimmed slightly.

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 carries the return-shape burden and does so well: per-contribution rate, base, ceiling, official source and check date, plus monthly/annual totals and percent of gross. An agent knows what it will receive and how totals may be qualified.

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 every parameter is already documented in the schema (including the assumptions override example). The description adds no additional parameter-level meaning, so the 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?

States a specific verb+resource: the statutory employer cost of one employee in a country, explicitly scoped 'before any EOR fee'. That scoping distinguishes it from siblings like provider_fees and total_hiring_cost without opening any schema.

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 implicit use case (comparing statutory cost per country, not full hiring cost) is derivable from the 'before any EOR fee' and 'cost comparison' phrasing, but no sibling is named and no when/when-not condition is stated. Adequate but relies on inference.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuine context beyond that: the dataset vintage ('Data snapshot 2026-10-01'), the catalog size (76), the fields each entry carries, and an explicit scope limitation. It still says nothing about pagination or how entries are ordered, but this is a solid addition over the structured hints.

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?

Three compact sentences with no filler: scope and fields first, then snapshot date, then the disclaimer. Front-loaded and appropriately sized for a read-only catalog tool.

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 usefully names the returned fields (ISO code, currency, example salary, statutory employer cost), which compensates for the missing return spec. The only real gap is that filtering by region is never acknowledged, but for a one-optional-param read-only list this is close to complete.

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?

The single optional 'region' parameter is fully documented in the schema (100% coverage, with examples), so the schema does the heavy lifting. The description never mentions filtering, but per calibration a high-coverage schema sets the baseline at 3.

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 the scope ('Countries covered (76)') and enumerates the returned fields, so the agent can infer it is a catalog of supported countries. However, it never states the action as a verb+resource (e.g. 'List the countries supported...'), leaving the purpose to be read off the name/title. No explicit differentiation from compare_countries, which is the nearest sibling.

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 when-to-use guidance, no prerequisites, and no routing to alternatives such as compare_countries for actual comparisons. The only usage-adjacent content is the disclaimer 'Cost comparison, not legal or tax advice', which limits liability rather than guiding selection.

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

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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), yet the description adds substantive behavioral context beyond them: a fixed data snapshot date (2026-10-01), the 'quote only' sentinel for providers that publish no price, and per-provider coverage gaps. These details materially affect how an agent interprets results.

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 compact sentences, front-loaded with the core data description, followed by the sentinel-value rule, snapshot date, and disclaimer. Each sentence carries information; nothing is padding.

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 carries the burden of describing return shape and does so — fee, pricing-page URL, read date, uncovered countries, plus the 'quote only' case. Adequate for a two-optional-parameter read tool; only the absence of sibling routing keeps it from being fully complete.

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 both parameters are already documented. The description clarifies that country results also report per-provider coverage, reinforcing the schema's 'Also say whether each provider covers this country' note, but adds no new syntax or format guidance beyond it.

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 precisely what data is returned — published Employer of Record fees per employee per month across 14 providers — along with the fields bundled with each fee. It does not explicitly name how it differs from siblings like employer_cost or total_hiring_cost, but the resource is unambiguous.

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 context is implied by 'Cost comparison, not legal or tax advice', which signals the intended comparison use case. However, there is no explicit when-to-use guidance or routing to the sibling tools (compare_countries, employer_cost) that also deal with cost.

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

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

Annotations already establish readOnly=true and openWorld=false, and the description adds real value beyond them: the data snapshot date (2026-10-01), the 1-50 headcount range, and the explicit disclaimer that output is a cost comparison rather than legal or tax advice. It stops short of describing determinism, rate limits, or how assumptions alter the result.

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 tightly packed sentences with the core cost definition front-loaded, followed by snapshot date and disclaimer. Every clause earns its place, though the enumerated component list makes the opening sentence dense.

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 carries the burden of explaining returns, and it does: gross salary, statutory employer charges, provider fee, per month and per year. Combined with the snapshot date and the schema's coverage of the nested assumptions object, an agent has enough to call it correctly, though currency/units of the returned figures are not stated.

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 schema already documents salary, country, provider, headcount, assumptions, and salary_currency. The description adds only marginal semantics (month/year output framing, 1-50 headcount), which is the expected baseline 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?

States a specific resource (all-in cost of hiring via one EOR provider) and enumerates the cost components, monthly and yearly, plus the 1-50 headcount scope. It is clearly distinct from a generic salary lookup, but it never names or contrasts with near siblings like employer_cost or provider_fees, so an agent must infer the boundary.

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 (a cost comparison for a given country + provider), and the 'not legal or tax advice' line bounds the tool's remit. However, there is no explicit when-to-use versus employer_cost, provider_fees, or compare_countries, which are the most plausible alternatives.

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