BreckenWander Travel

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: it returns two URLs (trip_url and trip_page_url) and discloses that 'package-only flight fares become bookable when the trip includes a hotel or experience.' This is useful, non-obvious 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 four sentences, front-loaded with the primary purpose. Every sentence adds information: what it does, when to use it, how to pass parameters, and return values/edge cases. It is denser than necessary but still concise with no 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 moderate complexity (2 params, 1 required, output schema exists), the description covers the key aspects: inputs, outputs, when to use, and an important edge case (package-only fares). It does not mention error handling or prerequisites beyond 'fresh results,' but the output schema and annotations fill some gaps. Overall, it is sufficiently complete for an agent to select and 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?

Schema coverage is 100% (both parameters have descriptions in the schema), so the baseline is 3. The description adds meaningful context beyond the schema by specifying that items are 'url values of the chosen flight, hotel, and/or experiences' and that they must come from 'fresh search results,' which adds clarity about the expected input format and freshness requirement.

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 'assemble[s] a complete multi-part trip' into 'ONE bookable link with a single checkout,' which is a specific verb+resource. It is easily distinguished from sibling search tools, as this is the only tool that builds a trip rather than searching for items.

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 it: 'whenever the user wants to plan or book a whole trip rather than a single item.' It also implies a prerequisite (passing values from fresh search results). While it does not name an alternative tool explicitly, the 'rather than a single item' exclusion provides clear 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 the description reinforces with 'does not book or take payment.' It adds the behavior of returning a booking link and the 'from' price in USD, which goes beyond the safety 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 concise sentences covering purpose, price, link, read-only status, and integration with build_trip. No filler, all sentences earn their 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?

With an output schema present, the description does not need to enumerate return fields. It covers purpose, safety, output link, and integration, making it sufficiently complete for an 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?

Schema covers 100% of parameters with descriptions; the tool description adds no parameter-specific details beyond the schema, so 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 uses specific verb 'Search' and resource 'tours, activities, and experiences' plus destination. It distinguishes from sibling tools (search_flights, search_hotels) by focusing on experiences and mentions integration with build_trip.

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 clear context: search experiences for a destination, returns a link, read-only not booking. It tells the agent to combine with build_trip for a full trip. However, it does not explicitly name alternatives like search_flights as alternatives; it only points to complementary use.

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 destructiveHint=false, and the description reinforces this by stating 'does not book or take payment'. It adds valuable behavioral detail: prices are per-traveler and include taxes/fees, and the returned link opens the same search for booking completion. This goes beyond the annotations in describing what the tool actually returns.

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

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

Three sentences: the first states the action, the second describes the return value and booking link, the third confirms safety and integration guidance. Every sentence earns its place, with no fluff or repetition. Front-loaded with the main 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 complexity (11 params, output schema present, clear annotations), the description covers all essentials: scope (round-trip), pricing inclusivity, booking link, safety, and how to combine with other tools. The output schema exists, so return values are already documented. The description is complete for an agent to select and invoke this tool appropriately.

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% as every one of the 11 parameters has a description in the input schema. The tool description only vaguely references 'two airports', 'given dates and travelers', which maps to the obvious required parameters but adds no new parameter-level details beyond the schema. Baseline of 3 is appropriate since the schema carries the parameter semantics.

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 begins with the specific verb 'Search' and the resource 'round-trip flights between two airports', making the tool's core function immediate and unambiguous. It distinguishes from sibling tools (search_hotels, search_experiences) by explicitly focusing on flights and mentioning integration with build_trip for combined trips.

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 this tool is for round-trip flight searches and is read-only, which helps set expectations. It also points to build_trip as the way to combine flights with hotels/experiences, giving a clear usage context. However, it does not explicitly state alternatives for one-way searches or when to prefer a different tool, though the sibling names make this reasonably inferable.

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 'Read-only: does not book or take payment' and 'Returns a link to complete the booking,' which goes beyond the readOnlyHint annotation. This clarifies the safe interaction and the tool's output. No contradictions 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 three sentences with no filler. The core action is stated first, followed by return behavior and read-only note. It is efficient and structured well.

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 12 parameters and an output schema, the description provides sufficient high-level context. It mentions the essential inputs (destination, dates), return behavior, and safety. The schema covers parameter details, and output schema handles return values, so 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 schema description coverage is 100%, so the baseline is 3. The description adds context about all-in prices, which aligns with price filter parameters, but the schema already describes those. The description does not add significant meaning beyond the parameter 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 the tool searches hotels for a destination and dates, with a specific verb and resource. It distinguishes itself from siblings by focusing on hotels and all-in pricing, and mentions returning a booking link. This makes it clearly separate from search_flights, search_experiences, and build_trip.

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 implies usage for hotel searches and explicitly directs combining with flights and experiences via build_trip. It does not explicitly mention search_flights or search_experiences as alternatives, but the sibling list makes that inferable. No exclusion criteria are stated, but the context is clear.

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