seat-intelligence

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

No annotations provided, so description carries full burden. Discloses return structure ('scores, notes, dimensions, and a recommendation') which is helpful, but omits safety profile (read-only status), authentication requirements, or rate limits that would be critical for a complete behavioral picture.

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 with zero redundancy: purpose declaration, return value disclosure (compensating for missing output schema), and specific usage example. Every clause earns its place; front-loaded with the core action.

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 compensates for missing output schema by detailing return payload. All 3 parameters fully documented in schema. Minor gap: could clarify config_id relationship to aircraft or explicitly contrast with get_seat_score for single-seat analysis.

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 clear descriptions for config_id, seat_a, and seat_b. Description adds implicit value through the '14A or 22F' example showing expected seat format, but does not explicitly elaborate parameters beyond what schema provides. Baseline 3 appropriate for high schema 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?

Clear specific verb ('Compare') with resource ('seats') and scope ('side by side'). Explicitly distinguishes from siblings by specifying 'two specific seats' vs. get_best_seats (general recommendations) or get_seat_score (single seat analysis).

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 trigger phrase ('Should I pick 14A or 22F') and clear context ('deciding between two seats'). Lacks explicit naming of sibling alternatives, but the binary decision example effectively delineates usage scope vs. other tools.

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 carries full burden. Explains filtering/limiting but omits critical behavioral details: what 'highest-rated' algorithm entails, return format structure, error conditions (e.g., invalid config_id), or side effects. Adequate but minimal for a discovery tool.

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 zero waste. First sentence front-loads purpose and capabilities; second provides usage triggers. Examples are embedded efficiently. No redundant phrases or tautology.

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?

Achieves adequacy for 3-parameter tool with complete schema. However, lacks output description despite 'Has output schema: false'—should specify what gets returned (seat identifiers? scores? rankings?). Missing safety/permission hints due to absent 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 coverage is 100%, establishing baseline 3. Description echoes cabin enum values and limit purpose without adding deeper semantic context (e.g., config_id format patterns, that cabin omission returns all cabins). Examples implicitly map 'economy' to cabin parameter, providing marginal value beyond 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?

Clear verb ('Find') with specific resource ('highest-rated seats') and scope ('aircraft configuration'). Lists filterable attributes. Deducts one point for not explicitly distinguishing from sibling `rowhint_get_seat_score` (which gets scores for specific seats vs. finding optimal ones).

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?

Excellent positive guidance with natural language triggers ('Use when someone asks...'). Provides concrete examples mapping user queries to parameters. Lacks negative guidance (when not to use) or explicit sibling comparisons.

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 carries full burden. It discloses return content (total seats, cabin layout, best/worst seats, facilities) and the config_id discovery pattern. Could improve by mentioning error behavior (e.g., if config not found) or confirming read-only safety, but covers core behavioral contract well.

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 dense sentences with zero waste: 1) capability list, 2) usage trigger with example, 3) discovery workflow. Well front-loaded with the verb 'Get' and immediately scopable resource.

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 exists, but description enumerates return fields conceptually. Discovery use case explains relationship to sibling tools. Complete for a 3-parameter tool with full schema coverage, though exact return structure remains implicit.

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%, so baseline 3 applies. Description adds value via concrete example mapping ('American Airlines 787-9' showing airline/aircraft pairing) but doesn't expand on parameter formats beyond schema 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?

Excellent specificity: 'Get a summary of an aircraft configuration' names the exact resource and action. It clearly distinguishes from siblings by focusing on general 'overview' versus specific seat analysis (compare, score, best seats).

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?

Explicit when-to-use with natural language example ('Tell me about the American Airlines 787-9') and context ('general overview before choosing a seat'). Critically, it explains the discovery workflow: 'discover valid config_ids for other tools'—guiding users to invoke this before sibling tools.

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 provided, the description carries the full burden of behavioral disclosure. It successfully describes what data is returned (comfort assessment, recline data, proximity warnings), but omits safety information (read-only status, rate limits, caching behavior) that annotations would typically provide.

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 well-structured sentences where every clause earns its place: purpose declaration, return value specification, and concrete usage example. Front-loaded with specific action ('Get') and appropriately sized without redundancy.

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 exists, the description appropriately compensates by detailing return values (comfort metrics, warnings). It implicitly references sibling rowhint_get_config_overview through the use case example, though explicit differentiation from comparison tools would strengthen this further.

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?

Input schema has 100% coverage with clear descriptions and examples for both parameters (seat identifier format, config_id format with aircraft codes). The description adds a concrete usage example ('Is seat 14A good on the Delta 737-800?') illustrating semantic relationships between parameters, but with full schema coverage, baseline 3 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?

Excellent specificity with verb ('Get') + resource ('quality score', 'color rating', 'detailed notes') + scope ('specific airline seat'). Explicitly distinguishes from siblings (compare_seats, get_best_seats) through emphasis on singular seat analysis rather than comparative or list operations.

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 when-to-use guidance with realistic example query ('Is seat 14A good on the Delta 737-800?') and context ('before booking'). Lacks explicit 'when not to use' or explicit sibling comparisons, though the specific seat focus provides implicit differentiation.

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 provided, the description carries the full disclosure burden. It adds valuable domain context explaining that these seats 'are labeled as window seats in airline booking systems but where the fuselage structure blocks the view,' which clarifies the selection criteria. However, it omits operational details like return format, data freshness, or whether results include seat numbers vs. full objects, leaving gaps given the lack of output schema.

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 contains exactly three high-value sentences: two defining the concept/problem domain and one stating usage triggers. There is no repetition of the tool name or schema contents. The structure front-loads the what before the when, making it easy to scan.

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 single-parameter lookup tool with 100% schema coverage, the description adequately covers the input side and functional purpose. However, with no output schema present, the description should have indicated what data is returned (e.g., seat numbers, row identifiers, or full seat objects). This gap keeps it at minimum viability rather than comprehensive.

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 the single parameter 'config_id' already documented as 'Aircraft configuration ID'. The description references 'a specific aircraft,' which loosely maps to this parameter, but adds no additional syntax guidance, validation rules, or format examples beyond what the schema provides. This meets the baseline for high-coverage schemas.

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 precise definition: 'List all window-position seats that have no actual window on a specific aircraft.' It uses a specific verb (List) and a well-defined resource subset (window-position seats lacking windows). It clearly distinguishes from siblings like get_best_seats or compare_seats by focusing specifically on identifying obstructed-view positions rather than ranking or comparing seats.

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 includes a dedicated 'Use when' clause that lists three specific trigger scenarios: when asking about window seats, wanting to avoid windowless positions, or choosing between window seats. This provides clear contextual guidance, though it stops short of explicitly naming sibling alternatives or stating negative conditions (when NOT to use it).

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 of behavioral disclosure. It describes the tool's interactive nature ('walks them through it via elicitation') and output format ('top 3 seat recommendations with notes'), which adds value. However, it lacks details on error handling, response time, or any limitations (e.g., data availability), leaving gaps in behavioral context for a tool with conversational elements.

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 and efficient: it starts with the core purpose, details the elicitation process, and ends with usage guidelines—all in two sentences with zero waste. Every sentence earns its place by providing essential information without redundancy.

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 (conversational, multi-step elicitation) and lack of annotations or output schema, the description is mostly complete. It explains the process and output format well, but could benefit from mentioning potential constraints (e.g., supported airlines or data sources). However, it adequately covers the tool's purpose and usage, compensating for the missing structured fields.

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%, with one parameter ('flight') fully documented in the schema. The description adds minimal semantic context by noting that 'flight' is optional and will be elicited if omitted, but this doesn't significantly enhance the schema's information. Since the schema does the heavy lifting, the baseline score of 3 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?

The description clearly states the tool's purpose: it's a 'conversational seat picker' that 'asks the user a few structured questions' and 'returns the top 3 seat recommendations with notes.' It specifies the exact elicitation process (flight, route length, priorities, cabin class) and distinguishes itself from siblings by handling users who haven't specified a seat or aircraft, unlike tools like 'rowhint_pick_seat' or 'rowhint_get_best_seats' which likely require more initial input.

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 this tool: 'Use this when someone wants help choosing but hasn't specified a seat or even which aircraft.' It contrasts with siblings by implying alternatives (e.g., if a user already has a seat in mind, other tools might be more appropriate), providing clear context for its application without 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It describes the output ('Returns top picks with scores and notes, seats to avoid, aircraft info, and a confidence rating'), which is helpful, but lacks details on potential limitations (e.g., data freshness, airline coverage) or error handling, leaving some behavioral aspects unclear.

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 appropriately sized and front-loaded, starting with the core purpose and parameters, followed by usage examples and positioning. However, the last sentence ('This is the easiest way...') could be considered slightly redundant with the earlier guidance, slightly reducing efficiency.

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 (4 parameters, no output schema, no annotations), the description is mostly complete: it explains the purpose, usage, parameters, and output. The main gap is the lack of output schema, but the description compensates by detailing the return structure, though not exhaustively (e.g., format of 'scores' or 'confidence rating').

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 the schema already documents all parameters thoroughly. The description adds minimal value by listing optional parameters ('cabin class, seat position preference, priority') without providing additional context beyond what the schema's enum descriptions offer, meeting the baseline for high schema 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's purpose with specific verbs ('Get the best seat recommendations') and resources ('for a specific flight'), distinguishing it from siblings like 'rowhint_compare_seats' or 'rowhint_get_seat_score' by focusing on personalized recommendations rather than comparisons or raw scores.

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 on when to use this tool with concrete examples (e.g., 'I'm flying AA1234 next week, where should I sit?') and positions it as 'the easiest way to get seat recommendations,' helping differentiate it from alternatives like 'rowhint_help_me_pick' or 'rowhint_get_best_seats' without naming them directly.

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 provided, the description carries full burden and does well by disclosing key behavioral traits: it returns a humorous, opinionated critique ('voice-y takedown', 'unvarnished truth') rather than factual data, and it will elicit missing parameters from the user. It doesn't mention rate limits, authentication needs, or error handling, but covers the core interaction style adequately.

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 perfectly front-loaded with the core purpose in the first sentence, followed by usage guidance in the second. Every sentence adds value: the first defines the action and output, the second provides explicit context for when to use it. 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?

For a tool with 2 parameters, 100% schema coverage, no output schema, and no annotations, the description is quite complete. It explains the tool's purpose, behavioral style, and usage context clearly. The main gap is lack of output format details beyond 'one-paragraph', but given the humorous nature, this might be sufficient.

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 the schema already documents both parameters fully. The description doesn't add any parameter-specific information beyond what's in the schema (e.g., it doesn't explain format constraints or provide examples beyond the schema's 'e.g., 31B'), so it meets the baseline for high schema 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 specific action ('roasts'), target resource ('a specific airline seat'), and output format ('one-paragraph, voice-y takedown'), distinguishing it from siblings like 'rowhint_get_seat_score' (neutral lookup) and 'rowhint_compare_seats' (comparison). The example query further clarifies the exact use case.

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 this tool ('Use when someone asks... they want the unvarnished truth, not a neutral lookup'), providing clear context and distinguishing it from alternatives like 'rowhint_get_seat_score' which would provide neutral data instead of a humorous critique.

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