Departi – Travel Compliance & Curated Booking

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

Annotations already mark the tool as read-only and idempotent. The description adds behavioral context with 'Advisory only,' indicating the tool provides analysis without binding decisions, which is valuable beyond 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 extremely concise with three short sentences, each adding distinct information: scope (43 countries), topics covered (treaties, DN regimes, social security), and nature (advisory only). 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?

Despite the tool's complexity (9 parameters, no output schema), the description lacks details on expected output, return format, or how to interpret the advisory. It does not cover how to formulate queries or what results look like, leaving 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 description coverage is low (33%), yet the description adds no parameter-specific meaning. It does not explain how to use key parameters like nationality, taxResidence, or duration, which are critical for the tool's function.

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: 'Tax residency analysis for 43 countries.' It specifies the verb (analysis) and resource (tax residency), and distinguishes from sibling tools like visa or accommodation checks by focusing on tax and including specifics like treaties and social security.

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 tax residency queries but provides no explicit guidance on when to use it vs. alternatives. It does not mention when not to use it or suggest other tools for different needs.

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 and idempotentHint, indicating safe, non-destructive behavior. The description adds behavioral context: covers multiple purposes, includes destination context, and personalizes when registered, which goes beyond 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?

Three concise sentences covering scope, purpose types, and personalization. No redundant information, front-loaded with key facts.

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?

Covers the tool's scope adequately but lacks detail on return format, data sources, or how personalization works. With no output schema, more guidance would be beneficial 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 67%, with descriptions for required parameters. The description reinforces the purpose parameter by listing examples, but does not add meaning for all six parameters. Personalization mention is a minor addition.

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 checks visa requirements for 43 European countries, covering multiple purposes (tourism, nomad, work, study, retirement). This verb+resource combination distinguishes it from sibling tools like departi_check_tax and departi_search_accommodation.

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 visa checking across various purposes and destination context. It does not explicitly state when not to use or provide alternatives, but the sibling context makes the scope 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. Description adds value by noting 'Requires auth' and listing profile contents, aligning with annotations without contradiction.

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-sentence description is highly concise, front-loaded with key information, and contains no redundant phrases.

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?

Adequately covers what the tool does and auth requirement. No output schema exists, but description provides a reasonable preview of return fields. Minor improvement could mention read-only nature explicitly, but annotations cover that.

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 with 100% coverage. Description adds no parameter details (unnecessary), so baseline of 4 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?

Description clearly states 'User profile' and lists specific data fields (preferences, travel history, subscription tier, compliance summary), making the tool's purpose distinct from all sibling tools which focus on searches or checks.

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 tool's purpose is clear and obviously different from siblings (search, check, track). However, it lacks explicit guidance on when to use or not use alternatives, though context makes it easy to infer.

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 safety and idempotency. The description adds that results are 'scored by traveler type' and 'returns booking links,' providing modest behavioral context. However, it does not elaborate on potential variations (e.g., pagination, result count) beyond what annotations hint.

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 sentence of 14 words, efficiently conveying the core purpose, a key feature (scoring by traveler type), and output (booking links). No fluff or redundancy—every clause 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?

With 10 parameters (3 required), no output schema, and moderate annotations, the description lacks completeness. It omits details on parameter usage, date formats, result limits, error handling, and output format beyond 'booking links.' For a complex search tool, this is insufficient for an agent to use it correctly without further inference.

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 30% (3 of 10 parameters described). The description mentions 'destination' and 'traveler_type' but provides no detailed semantics for other parameters like rooms, guests, locale, checkin, checkout, currency, maxPrice, persona. It compensates insufficiently for the low coverage, leaving many parameters unexplained.

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: 'Accommodation search across European destinations. Scored by traveler type. Returns booking links.' It specifies the verb (search), resource (accommodation), geographic scope (European destinations), and added value (scored by traveler type, returns booking links). This effectively distinguishes it from sibling tools (e.g., departi_search_experiences, departi_search_transport).

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 no explicit guidance on when to use this tool versus alternatives. It does not mention prerequisites, exclusions, or compare with sibling tools. While it implies usage for accommodation searches in Europe, it lacks context like when not to use or which scenarios are best suited for this tool.

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 non-destructive nature. The description adds 'Returns booking links,' confirming output format but omits details like rate limits or data freshness. Minimal addition beyond 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?

Three short sentences, no redundancy. Efficiently covers core purpose and output. However, lacks structured organization like bullet points or sections that could aid scanning.

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 5 parameters and no output schema, the description does not specify result format (beyond 'booking links'), pagination, or sorting. Annotations cover safety traits, leaving behavioral 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?

Only 60% of parameters have schema descriptions (persona, categories, traveler_type). The tool description does not elaborate on any parameter meaning or usage beyond the schema, failing to compensate for the 40% coverage gap.

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 resource ('Tours, activities, local experiences') and the action ('Search Experiences' implied by the name), with differentiation from siblings like accommodation and transport. The phrase 'matched to traveler personality' adds specificity.

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 implicitly indicates use for travel experiences, but lacks explicit guidance on when-not-to-use or alternatives. No prerequisites or context exclusions are provided.

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, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds context about return data (pricing, stops, booking links) and carrier types, but does not disclose rate limits, authentication requirements, or behavior on missing data. This adds some value but is not extensive.

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 very concise: a single sentence with clear components. It is front-loaded with the key action ('Flight search') and lists outputs. While effective, it could be slightly more structured to include usage context or parameter hints.

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 7 parameters, no output schema, and moderate schema coverage, the description is too minimal. It does not explain the response format, pagination, or what 'stops' means. The mode parameter (allowing 'ground' search) is omitted, which could lead to incomplete understanding. More context is needed for effective tool use.

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 57%, but the description adds no parameter-specific information. It does not clarify the purpose of the mode parameter or any other parameters beyond what is already in the schema. Missing parameter descriptions in the schema are not compensated for.

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 a 'flight search' tool covering budget and full-service carriers, and specifies return values (pricing, stops, booking links). This verb-resource combination is specific and distinct from sibling tools (accommodation, experiences, etc.), which cover different domains.

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 guidance is provided on when to use this tool versus alternatives. While sibling tools are in different domains, the description does not mention the mode parameter that could allow searching ground transport, potentially causing misuse. No when-not-to-use or alternative suggestions are given.

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=true and idempotentHint=true. The description adds that it is a calculator with warnings and persistent tracking when registered, which provides some behavioral context beyond annotations. However, it does not explain the implications of 'persistent tracking'.

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 short sentences, front-loading the purpose. It could include more detail but remains compact.

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 5 parameters including nested objects and no output schema, the description does not explain how the calculator works, what the output looks like, or the role of parameters like referenceDate or nationality. It is incomplete for effective use.

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?

With 0% schema description coverage, the description fails to explain any parameters (locale, entries, currency, nationality, referenceDate). It only mentions 'Schengen 90/180 calculator,' which does not clarify the meaning or usage of the input schema fields.

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 a 'Schengen 90/180 calculator' with tax residency warnings, which is specific and distinct from sibling tools like departi_check_tax and departi_check_visa.

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 does not provide guidance on when to use this tool versus siblings, such as departi_check_tax for tax checks. It implies usage for tracking Schengen days but lacks explicit context or exclusions.

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