Vedar — Kamchatka travel

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

Beyond the annotations (readOnlyHint=false, idempotentHint=false), the description reveals key behaviors: the request is confirmed manually by an operator by phone, it is not an immediate booking or payment, consent is mandatory for personal data, and unavailability causes the request not to be created while returning nearest free dates. This goes well beyond what annotations 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?

Five sentences, each carrying necessary information: purpose, precondition, operator confirmation/non-payment nature, no-availability behavior, and consent requirement. No filler or repetition; the most important usage constraint 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?

The description is strong for a tool with no output schema: it explains preconditions, non-instant nature, and the failure/no-availability branch. It does not describe what a successful response contains (e.g., request ID or 'submitted' status), but the operator-confirmation detail compensates somewhat for 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?

The input schema already covers all parameters at 100% with descriptions, so the baseline is 3. The description adds further operational meaning: 'consent: true' is required, availability must be checked beforehand, and the date must be a free date for the request to be created. This is valuable, though not extensive beyond 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 opens with a precise statement: 'Заявка на бронь конкретного тура на дату' — a request to book a specific tour on a specific date. It clearly separates this from sibling tools like create_lead and make_trip_plan by naming the exact resource (tour booking request) and the key parameters (tour, date).

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 the agent to verify availability via get_tour_availability before calling, and explains what happens when no seats are available. It also clarifies that this is not an instant booking or payment, setting expectations for when it should be used. It does not explicitly exclude alternative tools, but the precondition and behavioral clarifications are strong.

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 meaningful behavior beyond the annotations: the manager will call, the request is not a booking or payment, and the lead will not be created without consent:true. This is especially useful context for an agent deciding whether this is the right non-transactional action.

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 three tightly packed sentences with no filler. It front-loads the core action, then the essential requirements and privacy condition, and every sentence adds actionable guidance.

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 request-creation tool with no output schema, the description covers the purpose, required fields, side effect, and a critical precondition. The only minor gap is the absence of any mention of a confirmation response, but it is not essential given how focused and clear the rest is.

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 parameters are already documented, and the description adds practical semantics: it explains what comment should contain (dates, group composition, interests) and stresses that consent:true must come from a direct question. This goes beyond the schema and flags the failure condition.

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 opens with a specific verb and resource ('Оставить заявку на подбор тура по Камчатке') and immediately clarifies the tool's scope by stating 'Не бронь и не оплата — только заявка', distinguishing it from the sibling create_booking_request. This makes the tool's purpose unmistakable even without inspecting 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?

It gives clear context for when to use the tool: when a user wants to leave a tour-selection request and expects a manager to call. It also excludes booking/payment scenarios, though it does not explicitly name the alternative tool to use in those cases.

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 destructiveHint=false. The description adds behavioral details about the content returned (status, alerts, hazards, load, traditional knowledge) without contradicting annotations. It doesn't mention potential limitations or performance considerations, but for a read-only context tool this is acceptable.

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 concise—two sentences—with the core purpose and usage guideline front-loaded. Every word adds value, and it avoids redundancy with schema or annotations.

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?

No output schema exists, but the description enumerates the key information returned, which is helpful. It doesn't specify exact formatting or error scenarios, but for a read-only single-parameter tool, the description covers the essentials. A brief note on prerequisites or typical use cases could enhance completeness, but it's not critical.

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 provides 100% coverage for the single parameter 'place' with a description ('Название места или объекта'). The tool description does not add any further semantic detail about the parameter, so it relies entirely on the schema. Baseline 3 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 it retrieves comprehensive context about a place, listing specific data types (status, real-time alerts, hazards, load, traditional knowledge). It distinguishes itself from siblings like get_place_info by focusing on Guardian context, and the title 'Безопасность места' reinforces the safety-focused 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?

Explicitly instructs to use this tool whenever a specific place, volcano, lake, route, or source in Kamchatka is mentioned. The 'always' directive gives strong guidance, though it doesn't explicitly contrast with alternatives like get_place_info or safety_status, leaving some ambiguity for overlapping 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?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds behavioral context by clarifying the result is 'basic information' and that safety/alerts are deliberately excluded, pointing to get_guardian_context for that extra scope. 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 a single, front-loaded sentence with no filler. It states the core purpose first and then immediately gives the relevant sibling alternative, using every word efficiently.

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 one-parameter, read-only lookup tool whose annotations cover safety and idempotency, the description is sufficiently complete. It names the alternative for richer context, and no output schema is required for such a basic operation.

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 'name' is already documented as 'Название объекта'. The description adds no additional parameter-level meaning beyond what the schema provides, so the baseline score 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 and resource: 'Найти базовую информацию о месте из базы данных' (find basic place info from the database). It also differentiates the tool from get_guardian_context by pointing to that sibling for fuller context, so an agent can distinguish them clearly.

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 routes the agent to get_guardian_context when full context with safety and alerts is needed, implying get_place_info is for basic lookups only. This gives clear usage context, though it does not spell out other exclusions or 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds that data comes from 'real booking occupancy' and warns against using memory, which is useful behavioral context. However, it doesn't disclose response format, pagination, or what happens when no dates are available. With annotations covering the core safety traits, a 3 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 sentences with zero waste. The core purpose and data source are front-loaded, and the usage triggers and exclusion are packed into the second sentence. Every word 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 read-only lookup tool with full schema coverage and annotations covering safety, the description is nearly complete. It clearly tells the agent when to call it and what it returns conceptually. The only minor gap is the lack of detail about the response shape, but since there is no output schema and the tool is simple, the description is sufficient for correct 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%, so the schema already documents all three parameters. The description adds the critical instruction to always use this tool rather than memory, but it doesn't add parameter-level detail beyond the schema. Baseline 3 is correct 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?

The description states a specific verb ('get'), resource ('free dates and places of a specific tour'), and source ('real booking occupancy'). It explicitly distinguishes from memory-based answers and names the exact user queries it serves. This clearly differentiates it from siblings like get_tour_details and get_tours.

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 explicit when-to-use triggers: 'when a tourist asks when there are places, whether a date is free, which dates are possible.' It also gives a strong when-not-to-use rule: 'do not name dates and places from memory, only from here.' This is exemplary 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 already declare readOnlyHint=true and idempotentHint=true, so the safety profile is known. The description adds behavioral context: it explains the tool returns 'full details' of a specific tour and instructs the agent not to invent details but source them here. It provides value beyond the 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 two sentences, front-loaded with the essential purpose and content list, followed by explicit usage instruction. No superfluous words; every sentence earns its place. Example keywords in the schema add clarity without cluttering the 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?

For a single-parameter read-only tool with no output schema and full annotation coverage, the description is complete: it states what the tool returns (the listed details), when to use it, and instructs against fabrication. It doesn't specify return format or error handling, but given the simplicity and annotations, these are minor 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 schema already provides 100% coverage for the single parameter 'name', describing it as 'tour name or keyword' with examples. The tool description does not add any extra parameter-specific semantics beyond confirming the purpose, so the baseline of 3 applies since 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?

The description clearly states it provides full details of a specific tour, listing concrete aspects like description, program, meeting point, logistics, inclusions/exclusions, and what to bring. It distinguishes itself from siblings (like get_tours) by emphasizing 'specific tour' and instructing to use it 'always when tourist asks about a specific tour'.

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 ('use ALWAYS when tourist asks about a specific tour') and gives examples of queries (program, start, meeting, what to bring). It does not explicitly name alternatives or when-not-to-use, but the clear trigger condition and the instruction to always use for specific-tour queries adequately guide the agent.

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, and destructiveHint=false, so the safety profile is covered. The description adds useful context (scope: active tours; return contents: prices and dates) but does not go deeper into pagination, result limits, or why some tours might be excluded from 'active'. This is comparable to the calibrated baseline for annotation-backed tools.

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 first front-loads the core function, the second adds usage context. Everything present earns its place, and nothing important is repeated from the schema or annotations.

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 low-complexity tool (one optional parameter, fully documented schema, robust annotations, no output schema), the description covers the essentials: what it returns and when to call it. The main gap is not clarifying how it differs from get_tour_details/get_tour_availability in the usage guidance, but overall the tool is adequately specified.

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%: the single optional parameter activity_type is fully documented with concrete filter examples (рыбалка, вулканы, медведи, гейзеры). The description adds nothing about the parameter beyond what the schema provides, so the baseline score 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-resource pair ('Получить активные туры из платформы TourHab') plus return content (prices and dates), which clearly conveys what the tool does. It implicitly distinguishes from siblings like get_tour_details and get_tour_availability by emphasizing 'active tours' as a listing, but it never names those alternatives 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 second sentence gives explicit when-to-use guidance: 'Используй когда турист спрашивает о конкретных турах или программах.' However, it provides no exclusions or routing to alternatives, which matters here because 'конкретных турах' could plausibly overlap with get_tour_details, creating mild ambiguity.

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 false, so the safety profile is fully covered. The description adds no extra behavioral context, such as data refresh rates, caching, or response format. It is consistent with annotations but does not enrich them, which is acceptable given the annotations' completeness.

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?

A single, focused sentence with no filler. It front-loads the action and object, and every word is essential. The description is optimally concise for its simple purpose.

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 (no parameters, no output schema), the description is nearly complete. It specifies the location and the type of data (current weather). While it doesn't detail the output format (e.g., temperature units, conditions), this is a minor gap for a tool of this scope, and the description suffices for an agent to invoke it 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?

There are zero parameters, so the schema coverage is trivially 100%. The description does not need to explain any parameters, and it doesn't. Per the baseline for 0-parameter tools, a score of 4 is appropriate since no semantic clarification is required.

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 clear verb ('Получить' = get) and a specific resource ('текущую погоду' = current weather) with a precise location (Petropavlovsk-Kamchatsky). This unambiguously distinguishes it from all sibling tools, which are travel-related and none deal with weather. Even without explicit differentiation, the specificity makes the purpose unmistakable.

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 makes the usage context obvious: it is for current weather in that specific city. Since no sibling tool covers weather, there are no alternatives to compare, so explicit when-not-to-use guidance is unnecessary. The description implicitly covers the intended use case and leaves no ambiguity about scope.

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 read-only, idempotent, and non-destructive behavior. The description adds a concrete output trait: «Ответ содержит ссылку на страницу готового плана с бронью туров», which tells the agent the result is a link rather than a side effect.

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 cover what the tool does, when to use it, and what the answer contains. There is no repetition of schema field names and no 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?

For a tool with two optional parameters and no output schema, the description explains the output and the intent triggers clearly. The only real gap is not naming sibling exclusions, but the planning purpose is still clear enough for correct selection.

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 provides 100% parameter coverage, including the 7-day default and example interests. The description adds no parameter-level meaning beyond the schema, so the baseline of 3 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 opens with a specific verb and resource: «Собрать план поездки по Камчатке по дням», and lists concrete content zones, activities, prices, season warnings. It doesn't explicitly name a sibling alternative, but the trigger phrases make its planning role distinguishable from nearby get_tours and create_booking_request.

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?

«Используй, когда туриста интересует …» explicitly states when to invoke the tool, citing natural tourist requests. It lacks an explicit when-not-to-use statement or sibling exclusions, which keeps it slightly below 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 indicate readOnlyHint, idempotentHint, and destructiveHint=false. The description adds useful behavioral context by specifying the source (KBGS RAS) and that the result includes data freshness, which helps the agent interpret reliability. This goes beyond the 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 two sentences: the first states what the tool returns, and the second gives usage guidance and the sibling alternative. There is no wasted text, and the most important 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 the tool has no parameters and no output schema, the description fully covers what an agent needs: the scope, the content of the response, the data source, and when to choose this tool over get_guardian_context. Nothing critical 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?

The tool has zero parameters, so the description does not need to explain parameter behavior. The baseline of 4 applies because the schema is empty and the tool's aggregate scope is already described in the purpose and usage text.

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 defines the tool as returning the current safety situation for all of Kamchatka Krai, including active warnings, their count and severity, and data freshness. It explicitly distinguishes this tool from get_guardian_context, which is for a specific place.

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 when to use this tool: when asked whether it is safe to travel or what is happening in the region. It also explicitly points to get_guardian_context as the alternative for a specific location.

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 idempotentHint=true, so the safety profile is covered. The description adds platform/source context and output contents (prices and addresses), but does not disclose return shape, pagination, or any other behavioral details.

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 scope and output, the second gives an explicit usage trigger. No redundant words and no duplication of the schema.

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 search with three optional parameters, the description covers what the tool does and when to call it. There is no output schema, so a bit more detail on the returned structure could help, but the mention of prices and addresses is sufficient for most calls.

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 all three parameters are documented in the schema. The description adds no parameter-level meaning beyond the high-level mention of prices and addresses, so the baseline 3 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 names a specific action ('Найти жильё'), a concrete resource (accommodation on Kamchatka), and specifies provenance (TourHab platform) and included data (prices and addresses). This clearly separates it from siblings like search_transfers and search_gear.

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: use when a tourist asks where to stay, spend the night, or rent accommodation. It does not mention when not to use it or point to alternative tools, 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=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds that results come from TourHab and include daily prices, but does not disclose other behavioral traits such as output format, pagination, or behavior with no query.

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 states the action and scope, the second gives the usage trigger and concrete examples. Information is front-loaded and each sentence 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?

Given the low complexity (3 optional string parameters), rich annotations, and 100% schema coverage, the description is almost complete. It clearly covers purpose, trigger, and examples; the only minor gap is not describing the return list structure, but 'with daily prices' partially compensates.

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 parameters are already well documented. The description reinforces daily pricing and gives query examples, but does not add significant 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 uses a specific verb and resource ('find rental of tourist equipment in Kamchatka from TourHab with daily prices') and gives concrete item examples. It clearly distinguishes this tool from siblings like search_accommodations and search_transfers by focusing on gear rental.

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 explicitly states when to use the tool: 'Use when the tourist asks where to rent equipment' and provides examples. However, it does not mention when not to use it or name alternative tools, so it stops short of the highest rating.

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 destructiveHint=false, and the description is consistent with them. It adds valuable context beyond annotations: results show availability only, and a seat is occupied only after carrier confirmation, preventing agents from assuming the search reserves anything.

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, each with a distinct job: what the tool finds, when to use it, and the booking caveat. Nothing is padded and the main verb and resource appear first.

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?

Together with the fully documented schema and read-only annotations, the description is sufficient for correct invocation: it covers resource, scope, trigger phrases, returned data, and the no-reservation caveat. No output schema exists, but the description already sketches the result fields.

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?

Input schema describes all 4 parameters with formats and examples, so schema coverage is 100%; the description adds no new parameter-level detail. It does summarize what the search returns, which indirectly clarifies the meaning of 'place' and date window, but the schema already carries the semantic weight.

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 opens with a specific action ('Найти свободные места') and identifies the exact resource: Kamchatka carrier trips (jeeps, vans, minibuses) from the TourHab showcase. It also lists returned data fields, making the purpose unmistakable and clearly distinct from sibling search tools.

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 explicitly lists user intents that should trigger this tool ('как доехать', 'есть ли трансфер', 'заброска', 'попутный джип'). It does not name alternatives or state when not to use it, so it stops 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.