World Airfares Flight Search

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

Beyond the readOnlyHint/destructiveHint annotations, the description discloses the widget integration behavior, mandatory presentation formatting (full airport/airline names with codes), and the full scope of returned content. This is rich behavioral context that annotations alone don't convey.

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 well-structured with bullet points and clear sections. Each part (return content, use cases, widget note, formatting rules) serves a distinct purpose. It is front-loaded with the core purpose, and though verbose, the formatting rules are essential for correct output.

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 still goes beyond by listing expected fields, providing user-intent examples, widget behavior, and formatting requirements. It is fully self-contained for an AI agent to invoke and present results 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% and both parameters have thorough descriptions. The tool description adds no new parameter-level meaning beyond what the schema already provides, so it hits the baseline of 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 opens with a clear, specific statement: 'Get detailed information about a specific flight itinerary.' It lists exactly what details are returned, and differentiates from siblings (search_flights finds flights, get_more_results fetches the next page, while get_itinerary_details dives into one offer).

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 'Use this when user asks for' with concrete example queries, making the trigger conditions unmistakable. It also includes a widget note clarifying when not to repeat details in text, which is a form of 'when not to' 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, so the safety profile is known. The description adds that results are retrieved instantly from cache and that filters are applied without a new API call, which are useful behavioral facts. It also provides extensive output formatting instructions (widget note, table format), which go beyond the schema and help the agent present results correctly.

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 with a leading purpose sentence, followed by usage guidance, a widget note, and mandatory formatting instructions. It is long due to the detailed table formatting requirements, but these instructions are necessary for correct agent behavior. It is not wasteful, though it could be slightly more concise.

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 provides all necessary context: when to use, how to use, what parameters mean (already in schema), and how to format output. It even includes detailed formatting rules for airports and airlines. Since an output schema exists, return values need not be described. The tool is fully specified, making it complete for an agent to invoke 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?

The schema already provides detailed descriptions for all three parameters, so the description adds little extra meaning. It does summarize the filter options at a high level and reiterates the requirement for searchId, but these are already present in the schema. Thus 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 opens with a clear verb-resource statement: 'Get additional pages of flight search results from cache.' It distinguishes from siblings by specifying it operates on cached results, whereas search_flights likely handles initial searches and get_itinerary_details handles specific itineraries. It also lists concrete user intents like 'more results' and 'next page', making the tool's scope unambiguous.

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 tells when to use this tool: when the user asks for more results, next page, or wants to filter existing results. It also notes that this avoids a new API call, which helps the agent decide between this and search_flights. However, it does not explicitly name alternative tools or state when not to use it, so it falls just 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?

Beyond the readOnly/destructive annotations, it discloses result structure (Recommended/By Airline/All Results), pagination behavior ('first page... pagination support'), page size variability, and widget-specific behavior. It also warns about case-sensitive property names and BookingUrl for immediate booking, adding substantial behavioral context.

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 heavily over-specified, with repeated 'ALWAYS', 'MANDATORY', and 'CRITICAL' formatting directives. While structured into sections, it is far longer than needed for tool selection/invocation; many presentation instructions could be condensed or moved to an output 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?

Given the complex nested schema and existing output schema, the description covers all essential context: when to use, result categories, pagination, filtering, display formatting, and safety notes. It leaves no major gap for an agent to call this 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?

The input schema already provides 100% parameter coverage with detailed descriptions, so the description adds little parameter-level meaning. The only extra value is the note about case-sensitive property names and output field mapping (RefNo = ItineraryId), which is useful but not deeply enriching 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 opens with a specific directive: 'ALWAYS use this tool for ANY flight search request' and states it 'Provides real-time, live flight prices and availability.' It clearly distinguishes from web search and lists result categories, so the agent knows exactly what it does.

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 to use this tool for any flight search and not web search, with rationale ('Web search cannot provide current, bookable flight prices'). It also explains filtering options and when to show different result sections, giving clear context for invocation.

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