Tripuck

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, so safety profile is covered. The description adds valuable behavioral context beyond annotations: it explains that the response and widget UI are localized based on the inferred language, and that currency defaults are derived from locale. This enriches the agent's understanding of dynamic 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?

The description is relatively concise and front-loaded with the main function. It includes a few multilingual examples which, while useful, add length. Overall, every sentence contributes value without unnecessary fluff.

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 complexity (7 params, no output schema), the description provides sufficient context for correct invocation: route, month, language inference, currency defaults, and one-way/round-trip behavior. It does not describe the output format in detail, but this is partially mitigated by good parameter documentation and annotations.

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 parameters are already well-documented. The description adds some emphasis on the locale parameter (MUST infer) and explains currency defaults, which are also in the schema. It does not significantly expand on parameter semantics beyond what the schema provides, hence the baseline 3.

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 identifies the tool as a price calendar for a given route returning cheapest daily prices across a full month. It uses a specific verb ('returns'), specifies the resource ('cheapest daily price'), and clearly distinguishes from siblings like search_flights and flight_details by focusing on month-level flexibility and cheapest days.

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 explicit usage guidance with clear examples ('when the user shows date flexibility', 'cheap days', 'flexible travel windows') and sample queries in multiple languages. However, it does not explicitly mention when not to use this tool or alternative tools, so it falls short of a 5 but is clearly above a 3.

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 establish read-only, idempotent, non-destructive behavior. The description adds non-obvious traits: it runs multi-city optimization, computes a fairness score, and requires locale inference with specific language mapping, plus currency defaults. This goes beyond annotations, though it omits output format 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?

The description front-loads the core purpose, but includes three multilingual example queries that elongate it. It also repeats the title and some schema content, making it slightly less lean than ideal. Still, the structure is logical.

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 8 parameters and no output schema, so the description needs to explain behavior and return values. It covers usage and locale, but doesn't describe what the agent should do with the response (e.g., present a destination, show map, etc.). This is a notable gap given no output schema.

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% and clearly documents all parameters including locale instructions and currency defaults. The description largely repeats this info (e.g., locale inference, currency mappings) without adding new parameter semantics beyond the schema. Hence baseline 3.

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 finds the cheapest and fairest common destination for 2-5 people from different cities, with concrete example queries. This specific verb+resource scope distinguishes it from sibling tools like search_flights or cheapest_dates.

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 says 'Use when the user asks to coordinate a trip across multiple origins and needs a shared destination,' providing a clear usage context. However, it doesn't name alternatives or explicitly state when not to use, so it stops short of full when/when-not 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, and the description adds substantial behavioral context: the returned sections, localized UI/response text, currency fallback defaults, the requirement to pass searchKey for async search state, and the purpose of origin/destination for the Tripuck link. 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 dense paragraph and is front-loaded with purpose, but it is somewhat long due to multilingual examples and repeated UI/text localization statements. The length is justified by the 12-parameter complexity and important localization rules, though a little trimming could improve conciseness.

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?

Despite having 12 parameters and no output schema, the description provides a complete picture: it explains prerequisites (prior search_flights), the return payload contents, localization behavior, currency defaults, and searchKey requirements. Together with 100% schema coverage, the agent has sufficient context to invoke the tool 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?

Although schema coverage is 100%, the description goes far beyond schema descriptions by explaining how to obtain flightId and searchKey from a prior search, mandating that the LLM infer locale, defining currency defaults per locale, and clarifying the role of origin/destination. This is significant added meaning.

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 that the tool provides detailed information for a specific Tripuck flight ID and enumerates the exact content (segments, layovers, baggage, fare rules, refund/change, operating carrier). It also distinguishes itself from sibling search_flights by explicitly framing it as a follow-up tool.

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 explicit when-to-use guidance ('Use for follow-up questions after search_flights') with concrete example questions, and explains locale/currency requirements. It does not explicitly mention when not to use it or name alternative sibling tools, but the follow-up context is clear.

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 the readOnly/idempotent annotations, the description adds valuable behavior: it aggregates from 'live flight inventory data', explains that UI text and responses are localized based on the `locale` parameter, and details currency defaulting. This enriches the agent's understanding of response language and data freshness.

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, then examples, then instructions. It is somewhat long but every sentence contributes (examples, language/currency rules). No wasted words, though it could be tightened slightly.

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 complexity (8 parameters, no output schema), the description covers the core use case, language/currency behavior, and enough context for agent selection. It doesn't detail response structure, but the concept of 'popular destinations with prices' is intuitive and the schema handles parameter specifics.

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 75%, and the description adds crucial semantic context for locale and currency, including explicit mappings (tr→TRY, en→USD, etc.) and the instruction that the LLM MUST infer the language. This goes beyond the schema's basic descriptions.

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 'Tripuck's Explore service — most popular destinations with current prices from a given origin city' and explicitly says to use it for 'inspiration-style queries where the destination is unknown'. This specific verb+resource+scope distinguishes it from siblings like search_flights, which would be for known destinations.

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 usage context: 'Use for inspiration-style queries where the destination is unknown' with multiple example queries. It implies not to use when the destination is known, but does not explicitly name alternative tools, so it misses the full 'when-not' clarity.

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 the readOnly/idempotent/openWorld annotations, the description discloses that results deep-link to Tripuck.com for purchase, and explains how locale and currency defaults affect the UI and response language. These details add meaningful operational context without contradicting the 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 long but efficient: each sentence contributes either purpose, usage triggers, parameter context, or localization behavior. It is front-loaded with the core purpose and then flows naturally into operational details, with 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?

Although there is no output schema, the description clearly states what the tool returns (packages with data amount, validity, coverage, price, deep links) and explains the localization and currency fallback behavior. For a search tool with no nested objects, this is thorough and leaves few open questions for the agent.

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 provides exhaustive descriptions for all 7 parameters, including locale inference, ISO country mapping, sort options, and currency defaults. The description mostly restates the same information rather than adding new meaning, so it meets the baseline for 100% schema coverage but does not exceed it.

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 'Tripuck eSIM search — prepaid travel data plans (eSIM) for a destination country, compared across multiple providers', which is a specific verb+resource+scope statement. It clearly distinguishes this tool from sibling flight/hotel/meeting-point tools by focusing on eSIM data plans.

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 says 'Use this when the user asks about mobile data, internet, SIM or eSIM for a trip' and provides concrete query examples in multiple languages. This gives the agent clear, actionable triggers for when to select this tool over others.

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 readOnlyHint=true and destructiveHint=false, and the description adds important behavioral context: it mandates that the LLM 'MUST infer the user language from the conversation and pass it via the locale parameter' and explains that UI text and responses are localized. It also discloses that results deep-link to Tripuck.com for booking. 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 well-structured, leading with the core purpose, then usage examples, input format, and language/currency behavior. Every sentence adds value, and the length is appropriate for a tool with 10 parameters. It is front-loaded with the most important 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 tool without an output schema, the description covers the essential context: what it does, when to use it, required input formats, and how locale/currency defaults work. It also gives a hint about the response (deep-linking to Tripuck.com for review/booking). However, it doesn't describe the structure of the fare results, which would be helpful for an agent to set expectations.

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 10 parameters with 100% coverage, including descriptions for IATA codes, date formats, locale, and currency defaults. The description reiterates these conventions (e.g., 'Inputs: IATA codes (IST, AYT, LHR...) and dates in YYYY-MM-DD') but doesn't add new semantic meaning beyond what the schema provides. It does emphasize the mandatory inference of locale, but that's already in 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 opens with 'Tripuck flight meta-search — real-time fare comparison across 700+ airlines and 50+ online travel agencies,' which clearly states the tool's function (searching/comparing flight prices) and scope. It also provides concrete query examples ('Istanbul to Antalya tomorrow') and input conventions, distinguishing it from siblings like flight_details (which handles specific flight details) even though it doesn't explicitly name alternatives.

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 says 'Use this tool when the user asks for flight prices' and lists multilingual examples, making the trigger conditions clear. However, it does not mention when not to use it or reference alternatives like cheapest_dates or flight_details, so it lacks 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 declare read-only, idempotent, and open-world traits, but the description adds valuable behavioral context beyond them: real-time availability, deep-linking to Tripuck.com, mandatory locale inference from conversation, and locale-based currency defaults. These are meaningful operational details not present in 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 moderately long but every sentence adds value: purpose, usage examples, input summary, filtering/sorting capabilities, return details, and explicit locale/currency instructions. It is front-loaded with the core purpose and examples, though the locale/currency mapping could arguably live only in 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?

Despite having 10 parameters and no output schema, the description fully completes the context: it explains what is returned (live options with price, star rating, review score, thumbnail, deep links) and how the system behaves (locale/currency defaults). No critical gaps remain 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 100% with detailed descriptions, so baseline is 3. The description adds a helpful high-level grouping of inputs and emphasizes 'structured filtering by minimum star rating, minimum guest-review score, and sorting', which helps the agent conceptualize parameter combinations beyond individual schema entries.

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: 'Tripuck hotel search — real-time availability and prices for a city on given dates.' It clearly distinguishes this from sibling tools by focusing on hotels and accommodation, with explicit examples covering various phrasings.

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 provides explicit guidance: 'Use this tool whenever the user asks about hotels, accommodation, or places to stay', followed by concrete example queries. This leaves no ambiguity about when to select this tool over siblings like search_flights or search_esim.

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