평생요금제닷컴 알뜰폰 요금제 (Korea MVNO plans)

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 that the prices reflect the current moment ('지금'), implicitly contrasting with the price-history sibling, but says nothing about rate limits, ordering, or fallback when no plan matches a filter.

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 short sentences, front-loaded with what is returned before the routing hint and the filter options. Nothing is padded, though the filter sentence duplicates schema-level information and the quoted phrase is slightly awkward to parse.

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, zero-required-parameter query with no output schema, the description conveys the tiered result shape and the available narrowing filters. Annotations carry the safety profile, so only the exact return structure per tier is left implicit.

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 75%, so most parameters are self-documented, and the description usefully restates that results can be narrowed by 통신망(mno), 5G(network), and 통화 무제한(voiceUnlimited). The qosMin parameter is left to the schema, which is acceptable at this coverage level but adds no depth.

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 precise resource with an explicit scope: the cheapest lifetime-discount/regular plans for each of the 1/5/10/15/30/70/100GB tiers. The phrase 'use this first for "cheapest MVNO" questions' implicitly distinguishes it from siblings like search_plans and price_index. An agent can identify what it returns without opening the 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?

Gives clear context ('알뜰폰 최저가' questions, use first) and notes the result can be narrowed by carrier network, 5G, and unlimited voice. However, it names no alternative sibling tool and states no when-not conditions, so routing is only partially resolved.

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, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered. The description adds valuable behavioral context by listing the rich set of data returned (fees, tethering, SIM costs, price history, etc.), which helps the agent know what to expect from the call.

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 and followed by the actionable hint about where to get the id. The first sentence is a dense list of returned fields, but each item earns its place by informing the agent about output contents; there is no wasted wording.

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?

Given the simple one-parameter signature, full schema coverage, and annotations that cover safety behavior, the description is complete. It compensates for the absence of an output schema by enumerating what data is returned and explains how to obtain the required id.

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% and the single id parameter is well defined with a format example (e.g., joytel-617). The description adds meaning by specifying that the id should come from search or search_plans results, which is not stated in the schema and clarifies the value's origin.

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 (Fetch) and resource (one plan by id), then enumerates the returned data fields. It also directly names the sibling tools that produce the required id (search, search_plans), making it clearly distinguishable from search-style tools.

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?

Explicitly tells the agent to insert an id obtained from search or search_plans results, which provides clear context for when to use this tool. It does not state when not to use it or list alternative tools, but the intended workflow is unambiguous.

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, non-destructive, and closed-world, so the safety profile is covered. The description adds behavior-relevant context beyond that: it discloses the composition of the returned carrier records and notes that the SIM guidance is the carrier's verbatim source text, a useful provenance detail.

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 dense sentence with the scope ('per MVNO carrier') front-loaded and no filler. The bulleted field list is compressed into one line, which is efficient but slightly cryptic without punctuation separating concepts.

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 return content, and it enumerates the per-carrier fields adequately for a zero-parameter read-only listing. It stops short of stating list size or relationship to sibling tools, which is a minor 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?

The tool takes zero parameters, so per the rubric the baseline is 4; there is nothing for the description to clarify beyond what the empty schema already communicates.

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 makes clear this returns MVNO-carrier-level information (plan counts, network, cheapest lifetime plan, support phone, SIM guide), which separates it from the plan-search siblings like search_plans or cheapest_by_data. It is a noun-phrase enumeration rather than an explicit verb+resource statement, but the resource and its scope are 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?

There is no statement of when to use this tool versus the seven sibling price/search tools, no prerequisites, and no exclusions. The agent must infer usage purely from the return-field list.

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 the safety profile (readOnlyHint, idempotentHint, non-destructive), so the description is not burdened with that. It does add genuine behavioral context beyond the annotations: the data is refreshed daily from the official homepage and coverage begins at a 'record start date'. However, it never clarifies how far back the history goes or whether the series has gaps, which matters for a time-series tool.

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?

One compact sentence with the resource named first and the provenance/coverage caveat in a parenthetical. No filler sentences, and nothing important is buried.

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 single-parameter read tool with no output schema, the description conveys the essentials: what is returned conceptually (dated monthly prices for one plan), the data source, and the update cadence. The remaining gap is the undocumented id format, which is minor given the tool's simplicity.

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 0%, so the description must carry the weight. It does imply the lone 'id' parameter identifies a single plan ('요금제 하나의'), which adds real meaning over the bare string type, but it gives no format, source, or validity guidance for that identifier.

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 names a specific resource and scope: the dated monthly-price record for a single plan, sourced from daily checks of the official site. An agent can tell this is a per-plan historical price series, though it does not distinguish itself from close siblings like recent_price_changes or price_index.

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 statement of when to use this tool versus the obvious alternatives (recent_price_changes, price_index, cheapest_by_data). The only implicit cue is 'one plan', which hints at single-plan lookups, but no exclusions or comparative guidance are given.

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 a safe, idempotent, non-destructive read, so the safety profile is covered. The description adds that the index reports median and minimum values per month/data tier, but says nothing about the time span covered, refresh cadence, or output shape, which matters more given there is no output schema.

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 short sentences, with the core content (what the index compares) stated first and the use case second. Every clause carries information and there is no filler.

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 zero-parameter index tool, the description conveys what is measured and when to reach for it, and the annotations cover the rest of the safety profile. The remaining gap is return-value behavior (time range, granularity, format), which is not covered by an output schema and is only partially implied.

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 tool takes zero parameters, so there is nothing for the description to disambiguate — the baseline for a no-parameter tool applies. The description correctly implies the query is unfiltered by any argument, consistent with the empty 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 names a specific resource (MVNO price index) and states precisely what it aggregates: monthly median and minimum lifetime-plan prices compared per data tier. This is far more than a restatement of the name, but it never explicitly distinguishes itself from the sibling plan_price_history or recent_price_changes.

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 a concrete usage condition — trend questions such as 'are MVNO prices rising?' — which tells the agent when this tool applies. However, it offers no exclusions and does not name the alternative tools (plan_price_history, recent_price_changes) that could be confused with it.

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 the safety profile is covered. The description adds real value by disclosing provenance ('daily comparison of official homepage records'), which tells the agent how fresh the data is, but it says nothing about return shape, pagination, or what happens when no changes are found.

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 dense sentence that front-loads the time window and resource, then the returned fields, then provenance. No filler, though the embedded defaults/max duplicate the schema rather than earning their 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 an 8-parameter read tool with no output schema, the description does sketch the returned fields (changed date, before/after price), which partly compensates. But it leaves the direction/limit interaction, empty-result behavior, and the overlap with plan_price_history unexplained.

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 88%, so the schema already documents nearly every parameter, including the days range and default. The description merely restates 'N days (default 7, max 60)' and adds no syntax or interpretation beyond 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?

States a specific verb+resource: plans whose monthly fee rose or fell within the last N days, plus the changed date and before/after prices. Clear on its own, but it never distinguishes itself from the sibling plan_price_history, which sounds closely related.

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?

No when-to-use guidance, no exclusions, and no routing to alternatives such as plan_price_history or price_index. The only clarifying sentence explains data provenance (daily homepage comparison), not usage conditions.

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 (read-only, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds genuine behavioral context: the query is parsed for structured conditions, results are sorted low-to-high by monthly fee, and the data source is carrier official homepages (consistent with openWorldHint=false).

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?

Purpose is front-loaded, followed by input behavior, downstream routing to fetch, and examples. Dense but every sentence contributes; the mixed Korean/English phrasing is slightly heavy but appropriate for the bilingual domain.

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 a single required param and no output schema, the description does the needed work: it explains what the free-text query accepts, how results are ordered, and that the returned id feeds fetch for detail and price history. The one gap is not clarifying its relationship to the similarly named sibling search_plans.

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 already 100% with a one-line '한국어 검색어' description, so baseline is 3. The description earns above baseline by enumerating exactly what the free-text query is parsed for (데이터 GB, 월 요금 상한, 통신망, 5G, 통화 무제한, 통신사, 평생/기간/선착순) plus worked examples, telling the agent how to phrase input.

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 (search) and resource (Korean MVNO 요금제), and adds scope details: it reads conditions from a plain-Korean query and ranks results by lowest monthly fee from carrier official pages. An agent can grasp what it returns, though it never distinguishes itself from the lookalike sibling search_plans, which is a real ambiguity given the near-identical name.

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 description routes the agent forward explicitly ('결과의 id 로 fetch 를 부르면 세부 조건·가격 기록이 나옵니다') and gives concrete example queries, which is helpful. However, it gives no when-to-use/when-not guidance against the overlapping siblings search_plans and cheapest_by_data, so usage is only implied.

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, idempotent, non-destructive), so the description's value-add is the data-provenance context: results are based on carrier official homepages, refreshed five times a day, and each result carries source citation, verification timestamp, official URL, and current fee start date. That freshness and provenance detail is genuinely useful and not present in the annotations.

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: purpose first, then defaults, then result contents. Well front-loaded with no filler, though the parenthetical about refresh frequency could be folded more economically.

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 13-parameter tool with no output schema, the description is close to complete: it explains the defaults, the data source and refresh cadence, and what fields accompany each result, which compensates for the absent output schema. The remaining gap is guidance on narrowing versus broadening filters and pagination behavior.

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 92%, so the schema already documents nearly every parameter, including the enum meanings and the fee/data default values. The description restates the defaults (평생 할인·정가, 월 요금 낮은 순) but adds no syntax or format detail beyond what the schema provides.

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 (find) and resource (알뜰폰 요금제 / MVNO plans) plus the mechanism (조건을 칸으로 정해 — setting conditions across fields), which separates it from the single-purpose siblings. It does not explicitly name a sibling to contrast with, so differentiation is implicit rather than stated.

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 description implies multi-condition filtering is this tool's role, which distinguishes it from cheapest_by_data and price_index, but it never says when to prefer it or when not to. No prerequisites or exclusions are given, leaving the routing decision largely to inference from the sibling names.

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