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

No annotations are provided, so the description carries the full burden. It discloses that the output is 'short, practical guides' (implying static reference content, not live/mutating data), which is useful, but it says nothing about language, format, or personalization.

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 with zero filler; the purpose is front-loaded and the topic enumeration follows immediately. Every element earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-enum-parameter lookup tool with no output schema and no annotations, the description is nearly sufficient: it tells the agent what comes back and what topics exist. Minor gaps remain around output format and language, but nothing critical for correct invocation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, but the single parameter is an enum whose values the description simply restates ('airport, apps, emergency, transit-card'). The enum values are largely self-descriptive, so the description adds little semantic depth beyond the schema's own enum list.

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 resource (short, practical guides for visitors and foreign residents in Korea) with a clear verb-implied action of retrieving them. The topic list further scopes the content. It does not explicitly contrast itself with siblings like subway_route or korea_holidays, but the topic framing makes its domain distinct.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by 'for visitors and foreign residents' and the topic list, but there is no explicit when-to-use, when-not, or routing to siblings such as subway_route for transit directions or korea_holidays for holidays. An agent can infer the context but must decide on its own.

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?

No annotations are provided, so the description carries the full burden. It usefully discloses a non-obvious behavioral trait — substitute holidays are included — and that the tool has two modes (range vs single-date check). However, it says nothing about precedence when both 'date' and 'from'/'to' are supplied, timezone handling, or whether the range returns every calendar day or only holiday entries, which matters for a zero-annotation 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?

Two sentences with no filler: the first defines the action and modes, the second justifies usage. The critical capability statement is front-loaded, and no sentence restates the tool name or title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only lookup with three optional, fully documented parameters and no output schema, the description covers purpose, scope, and practical relevance adequately. The remaining gap — what happens if 'date' and 'from'/'to' are combined, and the shape of returned holiday records — is minor but non-zero, so this falls short of 5.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all three parameters including their defaults and date format. The description's split between 'date range' and 'check a single date' maps onto the schema's two modes but adds no format, default, or precedence detail beyond it. Baseline 3 applies when the schema does the heavy lifting.

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 specific verbs and resource: lists South Korean public holidays in a date range, or checks a single date. It also names the scope qualifier 'including substitute holidays' and 'South Korean', which cleanly separates it from the unrelated siblings (subway_route, subway_station, korea_guide). The two operating modes are stated up front so an agent can pick the right invocation mode 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 usage context ('useful for planning: many shops, banks and offices close, and transport is crowded around Seollal and Chuseok'), which tells the agent when this tool matters. It does not name alternatives or explicit exclusions, but the sibling tools are unrelated domains, so no routing ambiguity exists. Clear context without the 'when-not' clause keeps this at 4 rather than 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?

No annotations are provided, so the description carries the burden, and it does disclose the return contents (lines, transfer points, boarding direction, minutes, fare) and an operational trait (works offline, no API key). It omits error behavior for unrecognized or ambiguous station names and says nothing about data freshness for fares/times.

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 sentences, zero waste: purpose and scope first, accepted inputs second, outputs and the offline capability third. Every sentence earns its place and the most important information 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?

With no annotations and no output schema, the description compensates by describing both the operational model (offline, no key) and the return payload. For a read-only planning tool this covers everything an agent needs before calling 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?

Schema coverage is 100%, so the schema already documents all five parameters and their defaults, putting the baseline at 3. The description adds genuine meaning by stating that station names are accepted in English, Korean, Japanese and Chinese and that landmarks like Hongdae, COEX and Incheon Airport are valid inputs — helpful beyond the schema's example strings.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource — 'Plan a subway/metro trip ... between two stations' — plus a precise geographic scope (Seoul, Incheon, Gyeonggi). It is functionally distinguishable from subway_station, but it never names or contrasts with any sibling tool, so it falls short of the top tier.

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 clear: this is the tool for trip planning within the Seoul Metropolitan Area, accepting multi-language station names and landmarks. However, there are no explicit exclusions (e.g., 'not for other cities') and no routing to alternatives such as subway_station.

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?

With no annotations, the description carries the full burden and does reasonably well: it discloses accepted input languages, that typos are tolerated, and what the response contains (names per language, lines, coordinates). It says nothing about error behavior for unknown stations or any rate/scope limits, so it stops short of fully covering the behavioral profile.

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 the lookup action and immediately followed by input tolerance, return contents, and the primary use case. No filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description supplies the return shape itself (per-language official names, serving lines, coordinates), and the single input parameter is fully covered by the schema. Nothing needed to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for the single required query parameter, so the baseline is 3. The description adds value beyond the schema by stating that all four scripts are accepted and that typos are tolerated, which the schema description (examples only) does not convey.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('look up a Seoul-area subway station by name') with a clear geographic scope. It implicitly separates itself from subway_route by focusing on name lookup rather than trip planning, but it never names or contrasts a sibling explicitly.

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?

One usage cue is given: 'Use this to translate station names.' That implies the intended scenario but offers no when-not guidance and does not mention how it relates to subway_route or korea_guide when an agent is choosing between them.

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