kr-crypto-intelligence

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

The description adds value beyond the readOnlyHint and openWorldHint annotations by specifying the exact exchanges covered and noting the tool is free (no x402 payment required). It does not discuss rate limits or auth, but output schema exists and the annotations cover the safety profile, so the added context is sufficient.

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 compact sentences front-load the action and scope. The price note is a single short clause with an emoji, adding useful info without bloat. No wasted words.

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, read-only health check with an output schema and annotations, the description covers all necessary context: what it does, which connections are checked, and cost. There are no missing inputs or behavioral gaps.

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 has zero parameters, so there is nothing to explain. The baseline for 0 params is 4; the description appropriately focuses on behavior rather than parameter details.

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?

Description uses a specific verb 'Check' and clearly identifies the resource as 'service health and exchange connectivity status', naming concrete exchanges (Upbit, Bithumb, Binance). This distinguishes it from sibling tools which focus on market data, arbitrage, or news.

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 a health-check use case but does not explicitly state when to prefer this tool over alternatives or provide exclusions. Its unique scope is obvious relative to siblings, but without direct guidance the agent must infer when to invoke 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 readOnlyHint=true and openWorldHint=true. The description adds valuable context by stating it updates every 60 seconds, returns reverse premiums, and includes pricing/payment details. It does not contradict annotations and contributes practical operational transparency beyond safe-read status.

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 description is functional but slightly lengthy, with a clear split between functional details and payment/docs info. Every sentence contributes value, and the use of line breaks and emojis improves readability, though it could be trimmed without losing core meaning.

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?

Despite having an output schema, the description provides a rich, self-contained overview of the returned data (premium %, reverse premiums, gaps, flags, alerts) and practical usage context (price, payment, clients, docs). It is fully sufficient for an agent to decide whether and how to invoke this zero-parameter tool.

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 has zero parameters, so the baseline is 4. The description provides a thorough overview of what the scanner returns without needing to explain parameters, which is consistent with the empty input 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 tool scans Kimchi Premium for all tokens (180+) on Upbit and Binance, returning premium percentages, price gaps, and alerts. It uses a specific verb ('Scan') and resource ('Kimchi Premium') and distinguishes itself from sibling tools like get_kimchi_premium by emphasizing cross-exchange arbitrage scope.

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 gives clear context: 'Essential for cross-exchange arbitrage analysis.' It explicitly tells when to use it (for arbitrage analysis) but does not mention when not to use it or directly name alternative tools, so it falls short of full exclusion guidance.

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?

The annotations already declare readOnlyHint and openWorldHint, establishing the tool as safe and external. The description adds meaningful context beyond annotations by specifying the exact exchanges covered (Upbit, Bithumb, common) and stating the tool is free of charge, which is useful for agents evaluating cost.

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 description is extremely concise, with two clear sentences and a price note. It front-loads the action ('Get all available trading symbols...'), and every sentence contributes value without redundancy.

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 tool's simplicity (zero parameters) and the presence of an output schema, the description sufficiently covers purpose, usage context, and return scope. It also includes the pricing detail, which is relevant for other tools in the family.

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 has zero parameters, and the schema coverage is 100%, so the description carries no parameter burden. The baseline for no parameters is 4, and the description appropriately adds no unnecessary parameter details.

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 tool's purpose: retrieving available trading symbols from Korean exchanges, specifically naming Upbit and Bithumb. It distinguishes itself from sibling get_* tools by focusing on symbol availability rather than prices, alerts, or news.

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 explicitly instructs users to use this tool before calling other tools to check which symbols can be queried, providing clear usage context. However, it does not mention when not to use it or name alternatives, but for this generic symbol-listing tool such exclusions are not critical.

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 signal readOnlyHint=true, so behavioral burden is lower. The description adds valuable context: the detection mechanism ('comparing market list changes every 60 seconds'), the specific alert categories detected, and payment requirements ($0.01 USDC per call, x402 payment). This goes beyond annotations without contradicting them.

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 description is well-structured with a functional summary first, then payment and access details in a clearly separated block. It's slightly longer than necessary because of pricing/client info, but each sentence carries useful information for an agent deciding whether to call the 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 zero parameters and an output schema present, the description need not explain parameters or return values. It fully covers what the tool detects, how detection works (60-second polling), and the cost/access requirements, making it complete for an agent to decide and invoke 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?

The tool has zero parameters, so the schema provides no meaning to add. The description compensates by explaining what the tool does when invoked, satisfying the baseline for zero-param tools.

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 'Get Korean exchange alerts' and enumerates specific alert types (new listings, delistings, investment warnings, caution flags). This specific verb+resource combination distinguishes it from sibling tools like get_kimchi_premium or get_arbitrage_scanner.

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 notes 'Critical for risk management and early listing detection,' providing clear use context. However, it does not explicitly compare to alternatives or state when not to use it, so it lacks the explicit exclusion found in top-tier examples.

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=true, covering safety. The description adds behavioral context beyond that by specifying the cost ($0.001 USDC), the x402 payment requirement, supported blockchains, and client SDKs. This is useful disclosure of operational constraints.

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 description is front-loaded with the main purpose, then provides essential operational details in a structured list. The payment and docs lines are relevant and earn their place, though the emoji-heavy formatting adds minor noise.

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 simple zero-parameter tool with an output schema and read-only annotations, the description covers the core purpose, conversion use case, payment model, client options, and documentation link. It is sufficiently complete for an agent to select and invoke 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?

The tool has zero parameters, so the baseline is 4. The description adds meaning by clarifying the output is a rate for converting KRW/USD, which is helpful for understanding what the tool returns. No parameter documentation is needed.

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 starts with 'Get current USD/KRW exchange rate', which is a specific verb+resource combination. It clearly distinguishes this tool from siblings like get_kimchi_premium or get_kr_prices by focusing on the currency pair, and adds the conversion use case.

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 states 'Essential for converting between Korean Won and US Dollar prices', providing clear context for when to use the tool. However, it does not explicitly name alternatives or state when not to use it, so it misses the 'explicit exclusions' bar.

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 and openWorldHint. The description adds useful behavioral details such as 60s caching, the exact output fields, and the x402 payment requirement on multiple chains, which goes beyond the annotation information.

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 description is well-structured with clear sections for purpose, output, pricing, and parameters. While the Args block duplicates schema information, the overall organization makes it easy to scan and the content is front-loaded.

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 that an output schema exists, the description's coverage is adequate: it explains the purpose, output structure, cache behavior, payment method, and documentation link. It does not explicitly discuss when to use versus alternatives, 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?

Schema description coverage is 100%, and the description's Args section simply repeats the schema's symbol list and default value without adding new semantics. No additional parameter meaning is provided beyond the structured 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 tool's function: computing the premium between CoinGecko global price and Upbit Korean price with a short AI interpretation. It also highlights the 'light tier' nature, which differentiates it from the '_deep' sibling 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?

Usage context is implied through 'Light tier' and '60s cache', but there is no explicit guidance on when to choose this tool over related alternatives like get_kimchi_premium or get_global_vs_korea_divergence_deep. It does convey that the tool is paid, which is a relevant consideration.

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 mark the tool as read-only, and the description adds useful context: 5-min cache, 24h news window, and the returned field structure. It also discloses the per-call cost and payment method, which are behavioral traits. No contradiction with readOnlyHint.

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 description is front-loaded with the core 'Deep tier' purpose and then details return fields. The payment and docs lines add essential operational info, though the emojis and multi-line structure make it slightly longer than necessary.

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 one parameter, a full list of supported symbols, an output description of nested fields, and payment/cache details, the description covers all necessary invocation context. The output schema further reduces the need to explain return values, so the description is 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 schema already fully describes the single 'symbol' parameter with supported values and a default. The description repeats these supported symbols but adds no new semantic meaning beyond the schema, so the baseline of 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 clearly identifies this as the 'Deep tier' variant focused on Korean news signals and AI breakdown, distinguishing it from the base sibling get_global_vs_korea_divergence. It specifies the resource (global vs Korea divergence) and the added deep-analysis fields.

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 explicit when-to-use or alternative recommendations are given. The 'Deep tier' label implies it is for deeper analysis but does not state when to choose it over the base tool or other siblings. Payment details are provided but do not guide tool 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 indicate read-only and open-world behavior. The description adds essential operational details: the $0.002 USDC price, x402 payment method, supported chains, client libraries, and the exact return fields with their interpretations. This goes beyond what annotations provide, though it omits rate limits or error handling.

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 description is structured with clear sections (definition, payment, returns, args) and front-loaded with the core purpose. However, the 'South Korea ranks top 3 globally' sentence is tangential and the pricing/payment details could be moved to documentation, making it slightly more verbose than necessary.

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 an output schema present, the description doesn't need to explain return values, but it goes beyond by explaining the gap interpretation and the basis for each premium field. It also covers pricing, payment, and client compatibility, making it highly complete for a one-parameter tool. Minor gaps like rate limits do not detract significantly.

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 input schema fully documents the 'symbol' parameter with a description and default. The description adds a few more example values (SOL, DOGE) and reiterates the argument, but does not add substantial semantics beyond the schema. Baseline 3 is appropriate for 100% schema coverage.

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 uses a specific verb ('Get') and defines the resource (real-time Kimchi Premium between Upbit and Binance). It clearly explains the concept and the two premium metrics, which helps distinguish it from generic premium tools, though it does not explicitly contrast with sibling tools like get_global_vs_korea_divergence.

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 the tool is for real-time premium checks and provides an arbitrage use case ('Gap between the two premium values reveals real arbitrage margin'), but it does not explicitly state when to use this tool over alternatives or mention exclusions.

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?

Beyond the readOnlyHint and openWorldHint annotations, the description discloses key behaviors: aggregation from Naver, AI relevance classification, 5-minute cache, English translation, and the exact return structure. The payment and docs links also set accurate expectations for invoking the tool. No contradictions with 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?

The description is well-structured and front-loaded with purpose, followed by return format and parameter details. The payment block is verbose but contains necessary integration information. It earns its place despite a few extra lines about clients and docs which could be condensed.

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 single-parameter schema and annotations, the description is fully complete. It covers the return fields, caching behavior, payment requirements, and invocation prerequisites, leaving no critical ambiguity for the agent.

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 schema already fully describes the limit parameter with type, default, and range. The description repeats this information without adding additional semantics beyond what the schema provides. Baseline 3 is appropriate since schema coverage is 100%.

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 tool's purpose: retrieving Korean K-pop news, with specific detail on sources (Naver), translation to English, and AI classification. It effectively distinguishes itself from sibling tools like get_kr_news_semiconductor and get_kr_news_kpop_summary by focusing on K-pop content.

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 when to use the tool (when K-pop news is needed) but does not explicitly mention alternatives or exclusions. The sibling tools are named in the context, but the description itself does not guide the agent to choose this over others. The payment and client requirements are stated, but typical usage context 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?

Beyond annotations (readOnlyHint, openWorldHint), the description discloses a 5-min cache, payment via x402, and the AI synthesis behavior. This gives the agent critical operational knowledge without contradicting 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?

The description is front-loaded with the core purpose and uses clear sections for returns and args. The payment and docs information adds length but is operationally relevant; not every line is essential but overall it remains well-structured.

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 parameter, detailed return structure, and annotations, the description is largely complete. It mentions cache, payment, and output fields, though error handling or rate limits are not addressed.

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 input schema fully documents the only parameter, limit, with type, range, default, and description. The description repeats this information but adds no additional semantic meaning 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?

The description clearly states the tool retrieves Korean K-pop news with an added AI analysis layer. It explicitly distinguishes from get_kr_news_kpop by noting it is the same articles but with additional AI synthesis, making the purpose 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?

The description identifies get_kr_news_kpop as the base alternative and adds an AI analysis layer, implying when to use it for advanced insights. It provides useful context like a 5-min cache and payment requirement, but does not explicitly state when not to use it or list alternative tools.

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?

Beyond the readOnlyHint and openWorldHint annotations, the description discloses a 5-minute cache, payment requirements, and the return structure with English and Korean original fields for verification. Does not contradict 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?

Well-structured with clear sections for purpose, pricing, returns, and arguments. Includes a single-sentence usage rationale. No unnecessary fluff, though the emoji-prefixed payment details could be considered slightly promotional but still relevant.

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?

Covers purpose, cost, cache, return fields, and parameter constraints. The existing output schema and annotations fill in remaining details. Missing explicit error handling or date-time specifics, but for a simple read-only news tool it is sufficient.

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 only parameter 'limit' is fully described in the schema (1-10, default 5). The description repeats the same information without adding extra meaning beyond what the schema already 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?

Clearly states it provides Korean semiconductor industry news aggregated from Naver and translated to English, listing specific topics. Distinguishes from siblings like get_kr_news_kpop (different industry) and get_kr_news_semiconductor_summary (likely summary variant).

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 context that Korean chip news leads global semiconductor supply-chain signals, implying when this data is valuable, but does not explicitly name alternatives or provide when/when-not guidance relative to the summary sibling.

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=true. The description adds useful context beyond annotations: a 5-min cache, pricing/payment requirements, and the output structure including ai_analysis fields. No contradiction with 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?

The description is organized and front-loaded with the core purpose, followed by pricing, payment, and return details. It is longer than necessary, but each section (payment, cache, output) serves a clear purpose. The structure with headers improves scannability.

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 tool's moderate complexity, the description covers the main elements: input parameter, output fields (results[] and ai_analysis with subfields), cache behavior, and cost. An output schema exists, so return values need not be explained in detail; the description provides sufficient context for invocation.

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%, with the schema already documenting the 'limit' parameter (type, default, min/max). The description repeats this information ('Number of articles to analyze (1-10, default 5)') without adding new semantic meaning, so the schema carries the burden.

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 tool's function: 'Korean semiconductor news plus AI market synthesis.' It distinguishes itself from sibling tool get_kr_news_semiconductor by explicitly noting it adds an AI layer (sentiment, themes, market signal). This is a specific verb+resource+scope with sibling differentiation.

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 provides clear context by referencing its sibling tool get_kr_news_semiconductor and explaining the added value, implying when to choose this version over the simpler one. It also includes crucial payment instructions and cache behavior, but does not explicitly state when not to use it or describe alternative scenarios.

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 and openWorldHint. The description meaningfully adds that the tool is paid ($0.002 per call) and requires a micropayment client, which is essential behavioral context for an agent deciding whether to invoke it. It also clarifies return fields.

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 core purpose is front-loaded in the first sentence, followed by a structured payment section and clear argument list. Although it includes emojis and a docs link, each section earns its place; nothing is redundant.

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 output schema and annotations exist, the description covers purpose, payment requirements, argument semantics, and return fields. For a paid price-query tool with two optional parameters, this is complete and actionable.

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 descriptions cover both parameters, so baseline is 3. The description adds extra value with example symbols (SOL, DOGE) and explicitly explains the 'all' option for exchange, going beyond the schema's brief descriptions.

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 uses the specific verb 'Get' and identifies the resource as 'cryptocurrency prices from Korean exchanges (Upbit, Bithumb)', while also listing the returned data (KRW prices, 24h volume, change rate). This clearly distinguishes it from siblings like get_kimchi_premium or get_arbitrage_scanner.

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 usage context by naming the target exchanges and the type of data returned, but it does not explicitly state when to avoid this tool or mention alternatives. It provides clear context without exclusions.

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?

Beyond the readOnlyHint annotation, the description adds meaningful behavioral context: it discloses a 1-hour cache, the cost per call ($0.05 USDC), payment methods (x402 on Base/Polygon/Solana), and a documentation link. This is valuable transparency about operational aspects, though it does not cover rate limits or error 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?

The core description is efficiently written in three sentences, front-loading the purpose and outputs. The additional pricing/payment block is somewhat promotional but includes essential operational information, so it earns its place. Slight overuse of superlatives like 'First-in-world' and 'AI-powered' adds minor fluff.

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 zero parameters and an output schema, the description is contextually complete. It covers the tool's purpose, data sources, output structure, cache behavior, cost, and payment method. The documentation link further supplements implementation details, making this a well-rounded description for an AI agent.

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 input schema has zero parameters, so the baseline is 4 per the rubric. The description does not need to explain parameters, and any potential semantic meaning is irrelevant since no parameters exist. The description adds no parameter info, but that is fine given the schema's completeness.

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 tool's function: Korean crypto market sentiment analysis in English, combining exchange intelligence and Korean news context. It also enumerates specific outputs (sentiment label, score, English report, exchange signals, news context), making its purpose unmistakable and distinguishing it from sibling tools that focus on raw metrics like kimchi premium or price data.

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 usage context by detailing the combined data sources (exchange intelligence + Korean news) and positioning it as a unique sentiment API, but it does not explicitly specify when to use this tool over alternatives or provide exclusions. There is no mention of sibling tools or conditions that would favor another option.

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, but the description adds crucial operational details: the data sources, 15-min cache, $0.05 x402 payment requirement, and the nature of the AI note (factual, no trading advice). This goes well beyond the annotation and informs the agent of constraints and side effects (payment).

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 description is front-loaded with a clear definition, followed by output structure and contextual positioning. While it is longer than average, the additional payment info and docs URL are operationally necessary. The list-style formatting for returns aids scannability, though some redundancy exists between the prose and the returns list.

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?

The description covers all key aspects: data inputs, methodology, output components, regime/direction enum values, freshness, cache behavior, positioning, and payment requirements. The output schema exists, but the description still explains the return format in plain terms, making it highly complete for an agent.

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 has zero parameters, so schema coverage is 100% trivially. The description appropriately focuses on output semantics rather than input details, satisfying the baseline for a parameterless tool.

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 identifies the tool as a KRW Macro Stress Score calculator with a specific formula (5-component signal, 120d percentile) and output structure (score, regime, direction, breakdown). It explicitly distinguishes itself from kimchi premium tools with a validation note, making its unique purpose 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?

The description provides clear context that this is a KRW macro stress filter for trading bots and explicitly states it is not a kimchi premium predictor, offering a negative usage guideline. However, it does not directly name alternative sibling tools for comparison, only differentiates from kimchi premium.

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 indicate readOnly and openWorld, but the description adds significant behavioral details beyond them: exact thresholds (1-minute, >1%), the focus on volume spikes and top 20 tokens, and crucially, the monetization (cost per call, payment methods, required x402 SDK). This goes well beyond what annotations provide, with no contradiction.

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 core functionality is front-loaded in the first sentence and the following two sentences add useful context. However, the payment metadata (4 lines with emojis) is somewhat verbose and could potentially be condensed or moved to a separate metadata field, though it is structured and informative.

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 no-param read-only tool with an output schema, the description is comprehensive: it specifies the exchange (Upbit), time window (1-minute), criteria (>1%, volume spikes, top 20), and the monetization model. It fully equips an agent to select and invoke the tool 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?

The tool has 0 parameters, and the schema coverage is trivially 100%. Per rubric, baseline is 4 for 0-param tools. The description correctly adds no parameter information; it's unnecessary.

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 tool's purpose: 'Get Korean market movers' with precise criteria (1-minute price surges/crashes >1%, volume spikes, top 20 tokens by trading volume on Upbit). This specific verb+resource+metric set distinguishes it from sibling tools like get_kr_prices or get_kimchi_premium.

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 provides clear context: 'Korean retail activity often leads global price movements — early signal for traders.' This implies when to use the tool (for early trading signals) but does not explicitly mention alternatives or when not to use it, preventing a 5.

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?

The description adds substantial behavioral context beyond the annotations, including the $0.10 USDC per call cost, x402 payment requirement, supported clients, and documentation URL. It also clarifies the read-only nature by describing outputs rather than side effects, consistent with readOnlyHint and openWorldHint.

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 description is well-structured, leading with the tool's purpose and then providing concise bullet points for payment, client, and docs. Every sentence adds useful information with no redundancy or 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?

Despite the tool's complexity, the description covers the input (none), the data sources, the output shape, and the commercial/payment requirements. With an output schema present and no parameters, the description fully equips an agent to decide when and how to invoke it.

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 has zero parameters, so the schema is complete and there is no parameter ambiguity. The description adds no parameter details, but none are needed, so the baseline of 4 is appropriate.

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 tool provides AI-powered Korean crypto market analysis by combining multiple indicators, and it explicitly lists the output (BULLISH/BEARISH/NEUTRAL signal, confidence score, summary, raw data). This distinguishes it from sibling tools like get_kimchi_premium or get_fx_rate, which cover individual metrics.

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 establishes a clear use case: holistic Korean crypto market analysis with an AI-generated consensus signal. It implies this tool is for when a broad market read is needed rather than individual indicator data, though it does not explicitly name alternative tools or state exclusions.

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 and openWorldHint, so the agent knows it is a safe read operation. The description adds valuable context beyond this: the interpretation of the premium sign, the cost per call, the payment method (x402), and the required client SDKs. This provides meaningful behavioral/transactional transparency.

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 description is well-structured: the core purpose is front-loaded, followed by the interpretation of the output, and then cost/payment details in a clean bulleted format. Each line earns its place, though there are more sentences than the minimal ideal. It is concise without being terse.

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 parameterless, read-only tool, the description is exceptionally complete. It explains what the metric means, how to interpret positive/negative values, how it differs from Kimchi Premium, and adds critical operational details (cost, payment method, client options, docs). Given an output schema exists, the description does not need to explain return values. This fully equips the agent to decide when and how to invoke it.

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 input schema has zero parameters, so there is no parameter detail to clarify. The baseline for zero parameters is 4, and the description adds useful context about the underlying data source (Korean exchanges, official USD/KRW rate), though this is not strictly parameter semantics. It is adequate given the schema already conveys everything about parameters.

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 what the tool does: 'Get USDT and USDC premium on Korean exchanges vs official USD/KRW rate.' It also explains the meaning of positive/negative premium and explicitly distinguishes this tool from Kimchi Premium, differentiating it from its sibling tool 'get_kimchi_premium'.

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 provides clear context for use: it is a 'key indicator of Korean market fund flow direction' and explicitly notes it is 'separate from Kimchi Premium,' giving the agent a basis for choosing this tool over alternatives. However, it does not explicitly name or exclude the alternative tool for Kimchi Premium, so it falls short of a full when-to-use/alternatives specification.

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