korea-stay

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

Annotations only declare the mutation profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false). The description adds substantial context beyond that: retained data (arguments plus a 30-minute, 5-call summary scoped to the same access address), a shared-network caveat, an unauthenticated public-server warning, an hourly rate limit, and a privacy-policy link.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the gating condition and organized under clear headers, so the agent hits the critical constraint first. It runs somewhat long and the trailing parentheticals (shared-network mixing, CLAUDE.md rule 2) are dense, but each section carries actionable 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?

An output schema exists, so return values need no explanation. Given the mutation nature and zero required parameters, the description still covers authorization triggers, prohibited uses, retention/privacy, and rate limits — everything an agent needs to call it safely.

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 enum semantics of kind and the required/optional rules for problem and question are already fully documented in the schema. The description's 'kind=결함은 틀린 답 제보' line restates that schema text rather than adding new syntax or format detail, so baseline 3 applies.

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

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

States a specific verb and resource — relaying a user's error report or improvement request to the operator — and makes the trigger condition unmistakable. It is trivially distinguishable from the read-only stay_* siblings, which retrieve lodging data rather than write an operator report.

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

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

Explicitly partitions behavior: a dedicated '쓰는 때' section with quoted user phrasings that authorize the call, and a '쓰지 않는 때' section forbidding calls the user did not request or calls made before answering. Alternatives and exclusions are both named, leaving nothing to inference.

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

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

Annotations already cover readOnly/idempotent/openWorld/non-destructive, so the bar is lower, yet the description adds real value: it states the link is a search link (not a specific room/booking page), that availability is not checked, and that the query differs per platform (naver/google use name+address, tour uses name only, risking same-name collisions).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short paragraphs, front-loaded with the core action and followed by the key caveats. Every sentence earns its place; only a minor stylistic quibble keeps it from a 5.

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

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

With 100% schema coverage and an output schema present, return format need not be described. The description covers scope, non-booking semantics, and platform-query behavior, leaving nothing critical for correct invocation, though it could note anything about why stay_id must come from stay_search.

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 baseline is 3, but the description adds meaning beyond the schema by explaining what the platform choice actually does to the generated query (name+address vs name-only) and why tour results may be ambiguous.

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

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

The description names a specific verb and resource — it builds a link to the original platform's (Naver/Google/Tour) search results — and explicitly negates what it is not (a booking page). This lets an agent distinguish it from stay_search/stay_detail, though it does not name those siblings directly.

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 clearly frames the context: the server does not process bookings and sends the user to the original platform, which implies use when the user wants to proceed toward booking. There is no explicit statement of when-not to use it or which sibling to prefer instead, so it falls short of a 5.

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

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so the safety profile is covered. The description adds genuinely useful behavior beyond that: availability is always unknown because zero inventory channels are attached, the reason surfaces in unavailable_reason, and ledger_closure semantics are spelled out including the caveat that a missing closure record is not proof the business is open. It does not, however, cover pagination or response shape (output schema exists).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action, then the availability limitation, then the alternative tool, then the ledger caveat — a sensible priority order. It is somewhat long and the ledger paragraph is dense, but each sentence carries non-redundant 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?

For a read-only detail endpoint with an output schema, the description need not explain return values, and it goes further by interpreting ledger_closure and unavailable_reason fields and warning about the false-negative interpretation of ledger closure. Nothing needed to call or interpret this tool is missing.

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

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

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning the schema cannot: passing checkin/checkout/guests still yields availability=unknown, which tells the agent those parameters are inert for availability purposes. This is exactly the kind of semantic context the schema descriptions lack.

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 (숙소 하나의 상세 정보 조회) and enumerates the returned fields (이름·주소·좌표·종류·원장 출처). It also carves out a hard boundary against stay_search (id source) and stay_booking_link (availability/pricing), so an agent can route without opening schemas.

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

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

Explicitly says what this tool cannot do (재고 조회 불가, availability always unknown) and names the correct alternative with the condition that selects it (빈방·요금은 stay_booking_link로). Both the when and the when-not are stated.

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

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

Adds a genuinely non-obvious behavioral rule that no annotation covers: results with unknown availability are deliberately NOT filtered out, and 'unknown' must not be reported as sold out. This output-interpretation constraint goes well beyond readOnly/idempotent hints. It stops short of covering pagination or result-count behavior, which the annotation set does not provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with the core action before the caveat, and the bolded rule is the sentence that most needs emphasis. Efficient, though it is arguably minimal for a 7-parameter search with no usage framing.

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?

An output schema exists, so return values need no explanation, and the schema fully documents all seven parameters. The description supplies the key availability caveat but leaves the usage context relative to the three sibling tools unaddressed, leaving a real gap for a search entry point.

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 schema itself carries very rich parameter documentation (region matching, category vocabulary, checkin inventory behavior). The description adds no parameter-level detail, so the baseline 3 applies.

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

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

States a specific verb and resource with scope: '조건에 맞는 국내 숙소를 찾는다' (find domestic accommodations matching conditions). The domestic/Korea scope and condition-based search clearly separate it from stay_detail and stay_booking_link in spirit, though no sibling is named 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?

The description says how to interpret results but never states when to reach for this tool versus stay_detail or stay_booking_link, nor any prerequisites. Usage is only implied by the word '찾는다' (find); there is no explicit when-to-use or exclusion guidance.

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