MyNomadWorld: where should I live?

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

Annotations already declare readOnly/optional/idempotent and closed-world, so safety is covered and the description is free to add output shape instead. It does that well, listing the ten comparison dimensions and the conditional match-score addition when home_country is passed — valuable since no output schema exists. It stops short of saying how missing or invalid country names are handled or how the match score is scaled.

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 purpose before the dimension list and the conditional behavior. The run-on dimension list is dense but each item signals a distinct returned field, so little is wasted; a bulleted or grouped form would read faster.

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-value burden and does so by enumerating the compared dimensions, which is the key thing an agent needs to decide whether to call it. Gaps are minor: response format/structure and the ambiguity around home_country (the schema marks it 'Required.' while the required array omits it, and the description treats it as optional) are left unresolved.

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 60%, and country_a/country_b are entirely undocumented in the schema — the description only implies they are the two compared countries. It does add real meaning for home_country (drives the MyNomadWorld match score) and hints at monthly_income_eur via 'tax for their income', but says nothing about current_country's role, leaving the under-documented half partly uncovered.

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 and resource ('Side-by-side comparison of two countries') and enumerates the compared dimensions, so the agent knows exactly what output shape to expect. It is also clearly separable from country_profile (single country) and recommend_countries (multi-country search) by the 'two countries' framing, and from digital_nomad_visas by covering visa as only one of ten dimensions.

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 'for someone deciding where to move' clause gives a clear usage context, and the home_country conditional ('With home_country it also gives each one's match score') implies when to supply that optional param. It never names a sibling as an alternative or states an exclusion, so the agent must infer that country_profile is the right pick for a single destination.

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 safety (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, and the description still adds real behavioral detail: tax figures are conditional on income being supplied, and the current_country is explicitly left out of results. It also notes the return includes links to the full page. Minor gap: it labels home_country 'Required' while the schema does not require it.

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 purpose, with the content enumeration compressed into a single list rather than separate sentences. The long comma-separated list is dense but each item earns its place by telling the agent what comes back.

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 lookup with no output schema, the description adequately explains what data is returned and the conditional nature of the tax fields. It leaves only minor gaps, such as behavior for unknown or ambiguous country inputs.

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 the schema already documents all four parameters and the baseline is 3. The description reinforces purpose (income drives tax estimates, home_country drives distance/language) but adds little syntax or format detail beyond the schema, and its 'Required' note on home_country conflicts slightly with 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 clearly states the resource (a single country's relocation profile) and enumerates the concrete data it returns, so an agent knows exactly what it gets. Sibling differentiation is only implicit — it never names compare_countries or recommend_countries to signal that this is the single-destination option.

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 rather than stated: the phrase "living in one country" hints at a single-destination lookup versus the multi-country siblings. There is no explicit when-to-use/when-not or routing guidance toward compare_countries, digital_nomad_visas, or recommend_countries.

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 readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds value beyond that by disclosing the data source (MyNomadWorld dataset) and the shape of each result (income requirement, length, family option), which matters because no output schema exists. It does not mention default page size, ordering, or behavior when the income filter yields nothing.

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 sentence that front-loads the resource and dataset scope, then appends the optional filter. No filler or redundant restatement of the title.

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 3-optional-parameter read tool with strong annotations and no output schema, the description covers source, returned fields and the income filter adequately. The only meaningful gap is paging behavior around `limit`, which an agent calling a list tool would want to know.

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 67%: region and monthly_income_eur are already documented, and the description's income phrasing merely restates the schema's "at or below this" semantics. The undocumented `limit` parameter gets no explanation of its default or whether results are truncated, so the description does not compensate for the remaining coverage gap.

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?

Uses a specific verb ("Lists") with a precise resource ("countries that offer a digital nomad or remote-work visa in the MyNomadWorld dataset") and names the fields returned (income requirement, length, family option). It is distinguishable from country_profile and compare_countries by its list-shaped, visa-focused scope, but it never explicitly contrasts itself with the closest sibling, recommend_countries.

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?

"Optionally only those the user qualifies for on income" gives one conditional usage hint tied to the income filter. There is no statement of when to prefer this over recommend_countries or country_profile, and no exclusions or prerequisites, so the agent must infer the routing.

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 read-only/idempotent safety profile, and the description adds real value on top: the scoring dimensions (actual tax burden, cost vs. current country, safety, climate, sea, flight time, language, healthcare, residency ease) and the shape of the response (top matches with reasons, watch-outs and links). Minor gaps remain on failure modes (e.g., unrecognized home_country) but the behavioral picture is solid.

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?

Front-loads purpose, then the ranking factors, then extra filters, then the return shape — a logical ordering with no filler sentences. It is dense and long-ish, but every clause carries information.

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 14-parameter tool with no output schema, the description does the necessary work: it explains the recommendation logic, the optional narrowing filters, and what comes back (matches with reasons, watch-outs, links). Only edge behavior (invalid country, empty results, default limit behavior) is left unaddressed.

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 93%, so nearly every parameter is self-documenting; the description only restates the filter set (digital nomad visa, internet speed, time zone overlap) already spelled out in the schema. It adds light interpretive context by tying monthly income to "tax the user would actually pay" and current_country to cost/tax comparison, but that is baseline-level value.

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 and resource ("Ranks the countries that best fit a person who wants to move abroad") and anchors it with concrete user questions. The ranking/recommendation framing clearly separates it from compare_countries (comparison), country_profile (single-country detail) and digital_nomad_visas (visa lookup).

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?

Example phrasings ("where should I live?", "best country for me as a remote worker") give strong intake context for when this tool applies. It never names an alternative or an exclusion case, so it stops short of full when/when-not routing.

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