This Weekend (이번 주말)

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

Annotations already cover the safe-read profile, and the description adds real context beyond them: no model is called, matching uses the same rules and stemming as site chat, and the interpretation is reported back in a read field. It also discloses the date-fallback ladder, though it does not describe result shape or limit 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?

Front-loaded with the core behavior and the sibling routing comes last, which is the right order. It is dense and slightly repetitive with three example sentences plus repeated language notes, but each sentence carries information an agent needs.

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?

A conversational, rule-based lookup tool with an output schema (including the read field the description references), full parameter documentation, and an explicit fallback policy. Everything needed to invoke it correctly is present.

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 baseline is 3, but the description adds genuine meaning for previous — that missing topic, region, and date are inherited from the most recent prior question — beyond the schema's own wording. It also clarifies what the single question string may contain across languages.

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

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

States a specific verb+resource: reads date, region, and keywords out of one sentence and finds events with it. It explicitly contrasts with search_events for the case where date and region are already known, so an agent can tell it apart from its siblings.

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 concrete when-to-use examples in four languages, says what happens when no date is present (today through weekend, then widening to 60 days), how to chain follow-up questions via previous, and names search_events as the alternative when date/region are known. Nothing is left 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 declare readOnly, idempotent, non-destructive, non-open-world, so the safety profile is fully covered elsewhere. The description's added value is limited to naming the categories of data returned, without saying anything about missing/expired events, freshness, or rate 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?

One compact sentence that front-loads the keying mechanism (id) and then lists the payload. Nothing is redundant or padded, though there is no structure beyond a single clause.

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 required parameter at full schema coverage, an output schema, and rich annotations, the description needs to do little and it covers the essential what-and-by-what. A brief note on behavior for unknown or stale ids would close the remaining 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 single parameter already documents that the id comes from search_events results. The phrase '행사 id로' adds no syntax, format, or constraint information 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 states a specific verb (가져옵니다 / fetch) and resource (행사 / event) and enumerates what is retrieved: schedule, venue, fees, reservation guidance, source links. It is clearly a single-record lookup, distinguishable in practice from search_events, though it never explicitly contrasts itself with that sibling.

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 only implied: 'by event id' suggests this is a detail fetch following a search, but the description never says to use it after search_events or when to prefer it over ask_events. The only workflow hint ('행사 id from search_events results') lives in the schema, not the description.

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 this is a safe, read-only, idempotent, closed-world read, so the safety profile is covered. The description adds the key behavioral fact not in annotations: it exposes data freshness (last collection time) so the agent can judge staleness. Return formatting is left to the output schema, which is appropriate.

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: the first states what is returned, the second states the triggering condition. Nothing is wasted and the core purpose 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 zero parameters, a full output schema, and rich annotations, the only thing the description must supply is purpose and when-to-call, both of which are present. An agent can invoke this correctly with no further information.

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

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

The tool takes no parameters, so there is nothing for the description to disambiguate; the baseline for zero-param tools applies. The description correctly implies the call requires no input.

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

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

The description states a specific verb and resource: it reports the date range of the event data currently collected plus the last collection timestamp. That is concrete and distinguishable from get_report_status or get_event, though it never names a sibling tool 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?

It gives an explicit trigger — 'check this first when search results are empty' — which is a clear, actionable usage context tied to search_events. There are no stated exclusions or alternative-routing rules beyond that single condition.

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

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

Annotations already declare readOnly, idempotent, and non-destructive, so safety is covered. The description adds real value by disclosing the three outcome states and that a rejection reason accompanies a rejected status, telling the agent what result shape to expect.

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 with no waste; the core status-checking purpose is stated first, the rejection reason second, and the credential prerequisite last.

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 rich annotations, fully described parameters, and a separate output schema, the description only needs to frame purpose and outcome states, which it does. The only missing piece is any indication of error behavior for an invalid or expired editKey.

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 both parameters are already documented. The description only adds that the reportId and editKey are the ones received when filing the report, which is marginal provenance detail rather than a syntax or format clarification.

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: it reports whether a submitted report is under review, accepted, or rejected, and returns the operator's reason when rejected. Its purpose is clearly distinct from siblings like submit_event and report_event_change, though it never names them 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?

It states the prerequisite that the caller must have the reportId and editKey handed out at submission time, which implies the tool is used after submitting a report. There is no explicit when-not guidance or routing to alternatives.

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 that this is a non-read-only, idempotent, non-destructive tool. The description adds important process context: changed values must be supplied as arguments, and the change is applied only after operator approval.

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 four sentences, front-loads the purpose, then covers changed-value inclusion, approval, and the call trigger. It is dense and free of 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?

Given the full schema, output schema, and annotations, the description supplies the key missing context: operator approval is required and the tool should be called only when the user intends to report. No essential invocation context 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 100%, and the schema already documents all 18 parameters in detail. The description reinforces that only changed values should be included, but adds little parameter-specific meaning beyond what the schema provides.

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

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

The description states a specific action and resource: reporting that a mapped event's schedule, place, fee, or booking changed, or that the event was cancelled. It clearly separates the change and cancellation cases, but does not explicitly distinguish this tool from siblings such as submit_event or get_report_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?

It gives a clear trigger and a restriction: call only when the user says they will report an event change. It does not name the alternative tools for related tasks, so the routing guidance is strong but incomplete.

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

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description adds genuinely new behavior — the automatic synonym re-search with the terms reported in related, and the offset/nextOffset continuation rule. It does not discuss rate limits or result ordering, so it is not a 5.

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?

Four short sentences, front-loaded with purpose, then defaults, then pagination, then the fallback path. Every sentence carries information, though the pagination sentence partially duplicates the offset field description.

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 shape need not be explained, yet the description still names nextOffset and related, tying them to the workflow. Defaults are fully documented, leaving only ranking and result ordering unaddressed.

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; however, the description adds cross-parameter semantics that the schema does not spell out: omitting the dates defaults to the Korean-time weekend, and pagination continues by feeding nextOffset back into offset. That goes beyond field-by-field documentation.

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?

It combines a specific verb (찾습니다) with the resource (공개 행사) and the three filter axes (날짜, 지역, 검색어), so the agent can tell it is a multi-filter search rather than a single-record lookup like get_event. It does not explicitly contrast itself with ask_events or get_event_coverage, which keeps it at 4 rather than 5.

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 clearly states default behavior when date fields are empty (this weekend, Korea time), which is a usage condition, but it never says when to pick this tool over ask_events or get_event. Usage is implied by the filter descriptions rather than by explicit routing 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 only declare readOnly=false, idempotent=true, destructive=false; the description adds the substantive behavior: submissions land in a review queue and stay unpublished until an operator approves them, and duplicate detection returns the existing event instead of writing. Both are consistent with the idempotent and non-read-only hints.

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?

Four short sentences, purpose front-loaded, each carrying distinct information (queue target, required payload, approval gating, duplicate behavior, invocation condition). No filler, though the required-field enumeration partially restates what the schema mandates.

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 21-parameter, 13-required tool the description covers the create path well, and an output schema exists so return values needn't be explained. However it never mentions the second mode — editing a prior submission via reportId + editKey — nor the offline/hybrid restriction, both of which affect whether the agent should call this 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?

Schema coverage is 100%, so the schema already explains every field, including enums, formats, and bounds. The description enumerates the required set (schedule, topic, venue, coordinates, description, url) and explains why completeness matters for approval, but adds no format or usage detail beyond the schema; 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 ('지도에 없는 행사를 운영자 검토 대기열에 올립니다') and scopes it to events not already on the map. It doesn't name the sibling report_event_change, which handles corrections to existing events, so the boundary with that sibling must be inferred.

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?

'사용자가 제보하겠다고 할 때만 부르세요' gives an explicit gating condition, and the duplicate clause tells the agent not to create a new entry for already-mapped events. Missing is a named alternative (e.g. report_event_change for change requests), so the routing rule is clear but incomplete.

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