eFon: International Call Rates & Dialing Codes

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely new context about the response shape (dual-currency cheapest price, sorted ascending, per-country page URL), though it says nothing about behavior on invalid or ambiguous country inputs.

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 dense sentences with no filler: the first front-loads what the tool returns, the second front-loads when to use it, followed by examples. Everything 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?

There is no output schema, so the description carries the return-value burden and does so (prices in two currencies, ordering, country page URLs). With annotations covering safety and the schema covering both parameters, an agent has everything needed to call it correctly.

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 fully documented by the schema itself (formats for countries, language for names and links). The description adds only the comparison/sorting semantics, not new parameter 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?

The description gives a specific verb and resource (compare eFon call rates) and states exactly what comes back: cheapest per-minute price in EUR and USD, sorted cheapest to most expensive, each with its country page URL. That level of output specificity also separates it from the single-country get_call_rates 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?

It gives an explicit trigger condition ('when the user calls more than one country') plus two concrete example utterances, which strongly implies the not-for case (single country). It stops short of naming the alternative sibling for that case, so routing is inferred rather than stated.

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 read-only/idempotent/non-destructive, so the safety profile is covered; the description usefully adds that rates are caller-location-independent, that data is 'live', and it enumerates the returned content (rate lines, cheapest price, announced price change, page URL, app links). That return-shape disclosure is valuable given there is no output schema, though 'live' is not defined (refresh cadence / caching is unstated).

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 resource and granularity come first, followed by the return inventory, with usage triggers last — a sensible front-loaded order with no filler. The opening sentence is heavily comma-loaded, but every clause conveys distinct 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?

With no output schema, the description carries the return-value burden and does so by listing what comes back; annotations cover the safety profile and the schema covers both parameters fully. Only minor gaps remain: error behavior for an unresolvable country and what 'live' means in practice.

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 'country' (multilingual names, ISO code, dialing code) and 'language' (enum, default en) are already fully documented with examples. The description adds no parameter-level detail beyond noting that rates do not vary by caller, which justifies the absence of a caller parameter but does not extend the schema semantics.

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 resource precisely: per-minute eFon prices in EUR and USD for calling a named country, including the granularity of rate lines (mobile/landline/network). The scope ('a country', single-country lookup) implicitly separates it from compare_call_rates, but no sibling is named explicitly, so the agent must infer the boundary between this and the comparison tool.

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?

It supplies concrete trigger queries ('how much does it cost to call X', 'cheapest way to call X', 'is calling X from abroad expensive'), which maps user intent to the tool well. However, it never states when NOT to use it or names compare_call_rates/how_to_call as the alternatives for multi-country or dialing-instruction queries, so routing between siblings is left 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 declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine value by disclosing exactly what the caller receives (exit code, country code, example numbers, time difference/daylight overlap, guide URL, cheapest rate) and how omitting origin changes the output format.

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 purpose is front-loaded and the second sentence carries the one invocation rule. The middle enumeration of returned fields is long and slightly run-on, but with no output schema it earns its place by telling the agent what it will get.

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 correctly carries the burden of describing return content, and it does so thoroughly, including units like time difference and daylight hours. The remaining gap is routing relative to the three sibling tools, which 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 100%, so baseline is 3, but the description adds behavior the schema does not: omitting origin switches the result to the international (+) format only. That is a meaningful semantic rule about the optional param that an agent cannot infer from the schema alone.

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 a specific resource (eFon dialing guide) and its scope (calling a destination country from an origin country), with the exact contents enumerated. It is clear what the tool returns, but it never distinguishes itself from siblings like lookup_calling_code or get_call_rates, and the mention of the 'cheapest eFon rate' overlaps with rate-focused siblings without clarification.

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 only guidance is 'Omit origin for the international (+) format only', which explains one invocation mode but not when to choose this tool over lookup_calling_code or get_call_rates. Usage is implied by the purpose rather than stated, with no exclusions or alternatives named.

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/openWorld=false, so the safety profile is covered. The description adds substantive behavioral detail beyond that: shared-code handling, and that the result includes capital, example number, an eFon rate page, cheapest per-minute callback rate, and a one-ring scam warning. No auth/rate-limit caveats, but this is well above the annotation baseline.

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-loaded with the core purpose, and every clause (shared codes, example queries, return contents) earns its place. It is a single long run-on sentence with a slightly promotional tail ('Includes the cheapest eFon per-minute rate...'), which keeps it from a 5.

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: it names the country/countries, capital, example number, rate page and scam warning an agent will get back. Nothing an agent needs to call this correctly 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 coverage is 100%, so both parameters (code, language enum with default) are already documented, including the accepted formats. The description's mention of shared codes adds a little interpretation value but no syntax beyond the schema, 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 ('calling-code lookup: which country ... a code belongs to') and clarifies the shared-code edge case (+1, +7, +44). It is clearly distinguishable from siblings get_call_rates, compare_call_rates and how_to_call, which deal with rates and dialing procedure rather than country identification.

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?

Gives concrete trigger phrases ('which country is +36', 'who is calling me from +233', 'what does 00252 mean', missed call from an unknown foreign number), which is clear usage context. It does not, however, explicitly state when to prefer a sibling (e.g. how_to_call) or any exclusions, so it stops short of a 5.

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