Pixie Vacations Travel Booking

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

No annotations are provided, so the description carries the full burden. It discloses that the tool returns deep links and mentions 'no fees, same price as the cruise line,' but does not cover error handling, what happens with no results, or any side effects. For a search tool, this is adequate but could be more transparent.

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 waste. It front-loads the purpose, provides a usage example, and ends with exclusions. Each sentence serves a clear 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 has 6 optional parameters, no output schema, and no annotations, the description provides good context for what it does and when to use it. However, it does not cover all parameter combinations or explain what happens with empty inputs, leaving some gaps for complex queries.

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 only 33% (2 of 6 parameters have descriptions). The description adds context for some parameters (month, passengers, max_total_budget) but does not explain all, such as 'cruise_line' and 'destination'. It adds marginal meaning beyond the schema but does not fully compensate for the low 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 clearly states the tool finds a cruise by specified criteria (departure port, party size, month, budget) and returns deep links. It distinguishes itself from siblings by explicitly mentioning alternatives for Virgin Voyages and river cruises.

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 provides explicit when-to-use guidance ('Ideal for family cruise from Florida under $X style requests') and when-not-to-use with alternative tools ('For Virgin Voyages or river cruises, prefer search_virgin_voyages or get_river_cruise_info').

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?

No annotations provided; description does not disclose whether this is a read operation, authentication requirements, or any side effects. Merely lists returned data types.

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?

Single sentence with no extraneous words; front-loaded and efficient.

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 no output schema, the description should at least hint at the structure of returned data. Currently only lists categories; lacks detail on format or nesting.

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?

No parameters exist, so the description cannot add meaning beyond the schema. Baseline score of 4 applies for zero-parameter tools.

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?

Description clearly states it retrieves agency-level data (credentials, awards, booking options), distinguishing it from sibling tools that focus on specific bookings or resort searches.

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?

No explicit guidance on when to use this tool versus alternatives like get_cruise_booking_info or search_beaches_resorts. Usage is only implied by the generic 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?

No annotations are provided, so the description must carry behavioral disclosure. It mentions 'no fees' but does not describe what 'booking links' entails (e.g., are they direct links, affiliate links?), what happens if no results, or whether it is read-only. The scope is clear but behavioral specifics are lacking.

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: three sentences. The first states the core purpose, the second lists scope, and the third gives usage alternatives. No superfluous words.

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 3 optional parameters and no output schema, the description adequately explains the tool's role and when to use alternatives. However, it does not describe the return format or behavior for missing parameters, leaving some 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?

Schema coverage is only 33% (only cruise_line has a description). The description lists cruise lines but adds no additional meaning for destination or departure_month. With low coverage, the description should compensate but fails to clarify parameter usage or constraints.

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 returns cruise booking links for Pixie Vacations, covering a long list of cruise lines. It also distinguishes from siblings by specifying that dedicated tools should be used for Virgin Voyages and river cruises.

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 alternatives: 'For Virgin Voyages or river cruises specifically, prefer the dedicated tools search_virgin_voyages or get_river_cruise_info — they return more detailed ship/itinerary info.' This provides clear guidance on tool selection.

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?

No annotations are provided, so the description must disclose behavioral traits. It mentions returning a quote form and marketing text, but omits whether the tool is read-only, rate limits, or authentication needs. Minimal disclosure.

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 short sentence, which is concise but lacks necessary detail. It front-loads the purpose but sacrifices completeness.

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 3 optional parameters and no output schema, the description is incomplete. It does not specify the quote form's structure, how to use the return value, or what 'why Pixie beats direct' entails.

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 has 3 parameters with 0% description coverage, and the tool description adds no explanation for destination, budget_notes, or resort_preference. The agent has no guidance on what values to provide.

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 helps plan a Sandals or Beaches honeymoon and returns a quote form, distinguishing it from sibling tools like search_sandals_resorts which only search. However, 'Help plan' is somewhat vague.

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?

No explicit guidance on when to use this tool versus alternatives like get_sandals_beaches_deals or request_pixie_quote. The description does not mention prerequisites or context.

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?

With no annotations, the description must disclose behavioral traits. It correctly indicates the tool is a read-only URL retrieval, but it omits details like authentication requirements, error handling (e.g., invalid resort name), or whether the URL expires.

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 wasted words. The key information is front-loaded: purpose, scope, and a usage directive.

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 no output schema, the description should clarify the return value. It says 'co-branded booking URL' but does not specify the format (e.g., full URL string) or example. Still, for a simple URL retrieval tool, this is reasonably complete.

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 50% (only resort_name has a description). The description adds context by mentioning both brands (Sandals and Beaches), which aligns with the brand enum. However, it does not explain what happens if resort_name is ambiguous or misspelled.

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 'Get the co-branded booking URL for a specific Sandals or Beaches resort' with a specific verb and resource. It distinguishes from siblings like search_sandals_resorts by emphasizing it returns a booking URL, not search results.

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 instruction 'Always use this instead of direct sandals.com links' provides clear context for when to use the tool. However, it does not explicitly mention when to avoid it (e.g., use search tools for browsing) or list alternative siblings.

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?

No annotations are provided, so the description carries full burden. It mentions booking methods (online vs quote form) and a blog, but does not disclose behavior like what data is returned, authentication needs, or side effects. The tool's name suggests it returns info, but the description lacks transparency on output or limitations.

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 concise with four sentences covering purpose, specifics, and usage. However, the second sentence is quite detailed about a specific cruise (Celebrity, August 2027, Danube itinerary), which may be excessive and could be moved to a knowledge base. Some redundancy exists (e.g., repeating booking methods in different forms).

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 no output schema and three parameters, the description should cover return value, parameter usage, and limitations. It provides useful context on booking lines but omits what information the tool actually retrieves (pricing, availability?), how to interpret results, or any constraints (e.g., only future dates). This leaves gaps for the agent to infer.

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 67% with two parameters having descriptions listing values, but the tool description adds no additional meaning or format guidance beyond the schema. The third parameter (departure_month) lacks both schema description and tool description context. No examples or parameter relationships are provided.

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 retrieves river cruise booking info from Pixie Vacations, distinguishes between online-booking Celebrity River Cruises and agent-booked lines like Viking, and explicitly says to use this tool for river cruising queries. This effectively differentiates it from sibling tools like find_cruise or get_cruise_booking_info.

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 ends with 'Use this tool whenever a user asks about river cruising,' providing clear guidance on when to invoke. It also implicitly excludes non-river cruises by detailing the specific lines handled. However, it lacks explicit instructions on when not to use it (e.g., for ocean cruises) or 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?

No annotations are provided, so the description carries full burden. It mentions returning co-branded booking URLs, which adds behavioral detail, but lacks information on side effects, rate limits, or output structure.

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?

Single sentence, front-loaded with key purpose. No redundant 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?

Describes the core purpose and mentions booking URLs, but lacks details on output format or limitations. Since there is no output schema, the description should be more specific about what the agent can expect.

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 has zero parameters (100% coverage by default). Baseline is 4 for no parameters. Description adds no parameter info, but none is needed since there are no inputs.

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?

Clearly states it retrieves current deals and promotions for Sandals and Beaches resorts, including co-branded booking URLs. This distinguishes it from sibling tools like search_sandals_resorts or get_resort_booking_url, which focus on general search or booking.

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?

Implies usage for fetching promotions but does not explicitly state when to use it versus alternatives (e.g., search_sandals_resorts). No guidance on prerequisites or context.

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?

No annotations are provided, so the description carries the full burden. It explains the tool will recommend and connect to a planner, but does not detail what 'connect' means (e.g., form submission, link, email). The behavior is adequately described for an agent but lacks full side-effect transparency.

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-loading the action and ending with usage guidance. It is concise with no fluff, though the list of outputs is somewhat dense.

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 no output schema and no annotations, the description provides a high-level overview but omits details on input defaults, output format, or what happens after planner connection. It is minimally complete for an agent to infer usage.

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 has 5 parameters, all optional, but only 20% have descriptions. The description mentions outputs (resort tier, ticket package, time of year) but does not clarify how inputs like nights, party_size, or travel_month map to these outputs. It adds limited 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 clearly states the tool's purpose: recommending a Disney World resort tier, ticket package, and best time of year, then connecting to a planner. This verb+resource combination distinguishes it from siblings like find_cruise or get_resort_booking_url.

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 whenever a user asks about planning or booking Disney World,' providing clear context for use. It does not explicitly mention when not to use it or alternatives, but the sibling list implies other tools for non-Disney travel.

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?

With no annotations, the description must fully disclose behavior. It states it submits a quote request and returns a form with source tag and contact info, implying a read-like operation. However, it does not detail potential side effects or authorization needs, leaving some ambiguity.

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, with two sentences that front-load the primary purpose and then list use cases and outputs. It is efficient, but slightly more structure (e.g., bullet points) could improve readability.

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 9 parameters with low schema coverage and no output schema or annotations, the description provides adequate purpose and output summary. However, it lacks details on parameter requirements and return structure, which are needed for completeness.

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 only 22%, and the description does not explain any input parameters. It adds no meaning beyond the schema's minimal descriptions. The description should compensate for low coverage but fails to do so, leaving agents without guidance on parameter use.

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 submits a free quote request to Pixie Vacations and matches with a travel advisor. It lists specific use cases (family vacations, destination weddings, etc.) and distinguishes from sibling tools by emphasizing human agent support vs self-service online booking.

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 indicates when to use this tool, particularly for trips needing a human agent. It provides context on suitable scenarios but does not explicitly mention alternatives or when not to use it. Sibling tools exist for specialized bookings, but the description does not guide the agent to them.

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?

No annotations are provided, so the description carries full burden. It only states that co-branded URLs are returned, but does not disclose search behavior, potential side effects (likely none), or how parameters affect results. Basic transparency is missing.

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, concise sentence. It conveys the essential purpose without fluff, but could be slightly more structured for clarity. No wasted words.

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 is provided. The description only mentions the return of 'co-branded URLs' without detailing the structure, count, or pagination. For a search tool, this is incomplete; the agent lacks information about what the response contains.

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 67% with descriptions for two parameters. The description adds no additional meaning to the parameters. It does not explain how max_results behaves or the format of best_for values beyond the schema hints.

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 searches for Beaches Resorts, identifies them as family all-inclusive, and specifies the return type (co-branded URLs). This distinguishes it from siblings like search_sandals_resorts (adults-only) and other unrelated 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?

The description implies the tool is for family all-inclusive resort searches, but does not explicitly exclude alternatives or provide conditions for use. The sibling list helps differentiate, but the description itself offers no usage 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?

The description mentions returning co-branded URLs with a referral code, adding some behavioral insight. But with no annotations, it doesn't disclose other traits like read-only nature or side effects.

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 concise sentences, front-loaded with purpose. No redundant 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?

With 5 parameters, no output schema, and no annotations, the description is insufficient. It lacks details on result format, filtering behavior, or parameter usage.

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 only 40% (2 of 5 parameters described). The description adds no parameter details beyond the schema, failing to compensate for the low 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 clearly states it searches all 17 Sandals Resorts, specifying the resource and action. It distinguishes from siblings like search_beaches_resorts by explicitly stating 'Sandals Resorts'.

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 says 'Use when user wants a Sandals resort,' providing clear context. However, it lacks explicit when-not-to-use or alternative tools, though sibling names imply 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?

No annotations provided, so description must carry full burden. It implies a non-destructive read/search operation by describing what it returns, but does not explicitly state it is read-only, no authentication needed, or any side effects. The mention of a booking URL could imply a potential write or redirection, which is not clarified.

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, front-loaded with primary purpose. The second sentence lists return fields efficiently. The third sentence includes agent credentials which, while possibly useful for context, adds length. Still, overall concise and well-structured.

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 search tool with no output schema and moderate schema coverage, the description gives enough to understand what is searched and returned, but does not explain the output format or how to specify the 'departure_month' parameter. Differentiation from sibling 'find_cruise' is missing, making it less complete in context.

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 67% (ship and region have descriptions, departure_month does not). The description lists ship names and region examples but does not add formatting details or clarify the missing 'departure_month' parameter beyond what the schema provides. The value added over schema is minimal.

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?

Description clearly states what the tool does: 'Search Virgin Voyages adult-only cruises' and lists return values. It explicitly says when to use it (when user mentions Virgin Voyages or adult-only cruises). However, it does not explicitly differentiate from sibling tool 'find_cruise' which could also be used for cruise searches.

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 usage context: 'Use this whenever a user mentions Virgin Voyages or asks about adult-only cruises.' Lacks explicit exclusions or alternative tools, but the instruction is direct and actionable.

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