Korea Flight MCP

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

Annotations already indicate readOnly and idempotent. Description adds behavioral detail: terminal parameter is only meaningful for ICN and automatically converts inputs (e.g., T1 to P01). This goes beyond annotations without 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 description is long but well-organized with bilingual summary, examples, and parameter breakdown. Front-loaded with the key summary. Every sentence adds value, though could be slightly more concise.

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 complexity (3 parameters, conditional terminal), and presence of output schema, the description is complete. It explains terminal behavior, language options, and provides examples. No gaps for agent 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 coverage is 0%, but the description provides extensive parameter documentation: airport IATA, terminal ID mapping (with aliases), language options. Adds significant meaning beyond the schema's titles and defaults.

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 it provides an airport overview with today's volume, top airlines/routes, and terminal split. It specifies the resource (airport), scope (today), and distinguishes from sibling tools like incheon_arrivals and incheon_departure_congestion by being a broader overview. Examples reinforce the purpose.

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 examples and context (useful for first-time visitors), but does not explicitly state when not to use or alternative tools. The context is clear enough, but lacks explicit 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 indicate read-only, idempotent, non-destructive. Description adds the critical behavioral constraint that codeshare data is only available for ICN flights. 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?

Well-structured with bilingual title, description, examples, and parameter list. Slightly wordy but efficient for the information conveyed.

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?

Adequately covers the tool's purpose, parameters, and constraints. Output schema exists so return values need not be detailed. Parameter semantics are thorough.

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?

With 0% schema coverage, description fully compensates by explaining flight_id (with examples) and lang (with allowed values and tip to match user's language). Adds clear guidance beyond the bare 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?

Clearly states the tool provides codeshare info for ICN flights, specifying master flight number and partners. Distinguishes from siblings by noting ICN-only limitation and focusing on codeshare data as opposed to general flight status.

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?

Provides concrete examples of when to use (e.g., checking if a flight is a codeshare, finding master flight). Implicitly suggests not using for non-ICN flights, but lacks explicit contrast with sibling tools like get_flight_status.

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. The description adds important behavioral context: every line includes gate, terminal, and check-in counter; '-' means not assigned; historical data only for ICN on snapshot nights; up to 30 days back. This adds value 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 longer than average due to the rendering instructions and parameter details, but every part earns its place: the rendering note prevents critical data loss, and the parameter details are essential given 0% schema coverage. It's well-structured with a clear header, a rendering paragraph, and an Args list. Slightly verbose but justified.

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 tool has 4 parameters (all optional with defaults), an output schema exists, and annotations cover safety/idempotency. The description adds critical rendering instructions and parameter semantics. It lacks explicit return format details but the output schema exists, so that's fine. It covers the main complexity: rendering, date range, historical limitations, and language handling. A minor gap is not explaining what happens if an invalid airport code is passed.

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 carries the burden. It explains the format for flight_date ('today', 'yesterday', 'YYYY-MM-DD', up to 30 days back), the expected values for airport (IATA codes), direction ('arrival'/'departure'), and lang (must match user's language, default 'E'). This is useful because the schema has no descriptions or enums, so the description effectively compensates.

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 it looks up real-time arrival/departure status for 14 Korean airports, with a bilingual (Korean/English) front line. It specifies the resource (14 Korean airports) and the action (look up real-time info), and the rendering note further distinguishes it from siblings like incheon_arrivals or track_my_flight by covering multiple airports.

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 usage context for the data returned (rendering requirements, how to handle '-') and parameter usage (airport codes, direction, date, language matching). However, it doesn't explicitly state when to use this versus alternatives (e.g., incheon_arrivals for ICN specifics, track_my_flight for a specific flight), so it's clear but lacks explicit 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?

Beyond annotations (readOnlyHint, idempotentHint, etc.), the description discloses the time window (H-2~H+2), the specific data returned (schedule/actual time, aircraft gate, entry gate A-F, domestic/foreign passenger counts), and a language requirement. No contradictions with annotations; the description adds substantial behavioral context.

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 title line, a bilingual synopsis, examples, and parameter bullet points. It is front-loaded with key information. While slightly lengthy, every sentence serves a purpose; no redundant text.

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 0% schema description coverage and an output schema that likely details return values, the description is quite complete. It covers all parameters, time window, and language options. Minor missing aspects: no mention of pagination or error handling, but these are not critical for a straightforward arrival query. The output schema probably fills that 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?

With 0% schema description coverage, the description fully compensates by explaining each parameter: terno (terminal filter), airport (origin airport IATA), flight_id (specific flight), and lang (response language with options E/K/C/J). It provides defaults and examples, adding meaning beyond the bare schema properties.

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 '인천공항 입국 도착 정보' (Incheon Airport arrival info) with a specific verb 'arrivals' and resource. It distinguishes itself from siblings like get_flight_status and incheon_departure_congestion by focusing on arrival data with a time window and specific fields like entry gate and passenger counts.

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?

Examples explicitly show when to use the tool, e.g., 'How busy is Incheon T1 arrivals right now?' The description implies usage for real-time arrival queries but does not explicitly mention when not to use it or suggest alternatives like track_my_flight for tracking a specific flight. The context is clear but excludes some exclusionary 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?

Annotations already provide readOnlyHint, idempotentHint, etc. The description adds real-time update frequency (1-min) and per-gate granularity. No contradictions.

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 bilingual text and an example, but slightly verbose due to repetition. Still efficient for the content provided.

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 all essential aspects: functionality, scope (T1 only), real-time nature, and return data type. Output schema handles return details. No 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?

With 0% schema coverage, the description fully explains both parameters (terminal values and lang options) including pending status and language-matching tip.

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 it provides real-time per-gate wait counts for Incheon Airport departure hall, distinguishing it from sibling tools like incheon_arrivals and incheon_facilities.

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?

Includes an example query and notes T2 is pending, which guides usage. Could explicitly state when not to use or name alternatives, but sibling context provides comparison.

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, openWorldHint, idempotentHint, and destructiveHint. The description adds that queries are case-insensitive partial matches, language fallback behavior, and references a specific dataset. This adds useful context beyond 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 with a brief intro, example section, and argument list. It is slightly verbose but remains clear and front-loaded with key 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?

Given the output schema exists and annotations are provided, the description covers all necessary aspects for effective use: data source, filtering options, language behavior, and examples. It is thorough for a search 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?

All three parameters (query, area, lang) are explained in the description with example values and constraints. Schema has 0% description coverage, but the description fully compensates by defining each parameter's purpose and allowed values.

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 it is for Incheon Airport commercial facilities (~1,227 stores/services). The name 'incheon_facilities' matches, and examples demonstrate typical queries. It is distinct from sibling tools like flight status or congestion.

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?

Multiple examples illustrate when to use the tool, with various filters (query, area, lang). However, it does not explicitly state when not to use it or provide alternatives among siblings.

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 readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the agent knows it's a safe, non-mutating query. The description adds useful behavioral context: results are for today, bidirectional, and require a Korean airport on one side. This exceeds annotation coverage without 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 description is reasonably concise, using a brief Korean/English summary followed by examples and parameter documentation. Every sentence adds either context or usage guidance. Minor redundancy between Korean and English text, but overall efficient.

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 presence of an output schema, the description does not need to detail return values. It covers the essential behavioral constraints (today only, bidirectional, Korean hub). It omits edge cases like empty results or time zones, but for a query tool with good annotations, this is acceptable.

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 0%, so the description must fully document parameter meaning. It does: origin and destination are IATA codes with examples (GMP, ICN, YVR), lang offers 'E'/'K'/'C'/'J' with a recommendation to match the user's language. This adds significant value beyond the bare 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 uses specific verbs ('search', 'find') and clearly defines the resource ('today's flights between origin and destination'). It distinguishes from sibling tools like get_flight_status (specific flight) and incheon_arrivals (single airport) via the bidirectional requirement and Korean hub condition. Examples reinforce the 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 explicitly states when to use: flights between two airports, today, bidirectional, at least one Korean hub. It does not directly exclude alternatives or provide a when-not-to-use list, but the context from examples and sibling names implies differentiation. Could be improved by naming sibling tools for exclusion.

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 declare readOnlyHint, idempotentHint, and destructiveHint false. The description adds behavioral details beyond annotations: it explains the fallback mechanism (30-day snapshot DB lookup then 4-hub fan-out) when hub_airport is empty. No contradictions.

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 purpose in both Korean and English, followed by examples and parameter explanations. It is somewhat long but every sentence contributes value. Could be slightly tighter without losing clarity.

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 an output schema exists (though not shown), the description covers return values (times, gate, carousel, status). It explains all parameters and provides usage examples. It lacks explicit context on when to prefer siblings, but overall is fairly complete for the tool's scope.

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 0%, so the description carries full burden for parameter semantics. It explains flight_id (flight number), hub_airport (narrows search, with fallback behavior), and lang (response language with defaults). This adds significant meaning beyond the raw 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 tracks a flight to provide scheduled/estimated times, gate, baggage carousel, and status. It is specific to Korean airport real-time flight info. However, it does not explicitly differentiate from siblings like get_flight_status or airport_overview, but the focus on carousel and gate distinguishes it.

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 examples of when to use the tool (e.g., flight delay, arrival time, carousel) and highlights carousel for pickup. It does not provide explicit when-not-to-use guidance or compare with alternative sibling tools, leaving usage context implied.

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