SnowSure — Snow & Ski

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

Annotations (readOnlyHint, idempotentHint, destructiveHint) are consistent. Description adds behavioral context: ~1s response time, text-only, no UI cards, grounded in SnowSure data. No 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?

Description is front-loaded with core purpose and includes clear do's and don'ts. The list of use cases is somewhat lengthy but adds clarity; minor verbosity prevents a 5.

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 6 params, output schema presence, and sibling tool set, the description fully covers what the tool does, when to use it, and key constraints (no UI cards, grounded data). No 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 covers all 6 parameters with descriptions (100% coverage). Description does not add additional meaning beyond schema, but usage examples imply purpose of 'question' and 'resortSlug'. 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?

Description clearly states it's a text-only Q&A grounded in SnowSure data for specific use cases (open-ended questions, terrain%, comparisons, season openings, etc.) and explicitly excludes photo/gallery and resort guide card requests, distinguishing it from siblings like get_resort_photos and get_resort_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?

Explicitly states when to use (open-ended questions, comparisons, etc.) and when not to use (photo/gallery requests -> get_resort_photos; resort guide cards -> get_resort_info), with a concrete example of head-to-head resort 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?

The description adds significant behavioral context beyond annotations: it never charges, holds the rate, attributes the booking, and requires OAuth. Annotations provide idempotentHint and non-destructive, but description clarifies the exact flow.

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 at three sentences, front-loads the main purpose, and efficiently covers both modes and requirements with no unnecessary 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 output schema exists, the description handles all necessary context: dual behavior, authentication, and payment flow. It is complete for an agent to select and use 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 the description enriches parameter meaning by explaining the trigger condition for prebooking and the role of powderEventId. It adds value beyond the schema definitions.

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 two modes: providing availability + booking link, or prebooking with a checkout URL. It names the specific resource (lodging via LUXSKI) and distinguishes from sibling tools, none of which handle lodging 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 explains when to use each mode (with/without hotelName+dates) and mentions the OAuth requirement. However, it does not explicitly state when not to use the tool or compare to alternatives, though context makes it 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, and destructiveHint=false. The description adds value by specifying that the tool shows model agreement and uncertainty, which is behavioral context beyond the annotations. No contradictions.

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: first defines action and scope, second describes output, third gives usage guidance. Every sentence adds value with no redundancy or unnecessary 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?

The description covers the key aspects: models (7 named), time range (14-day), output (agreement/uncertainty), and use case. With an output schema present, return value details are unnecessary. It is sufficiently complete for the tool's complexity.

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 one parameter (slug) described as 'Resort slug'. The description reinforces that the slug identifies a resort but does not add new semantic details. Baseline 3 is appropriate as schema does the heavy lifting.

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 compares 14-day snow forecasts across 7 named weather models for a resort, and shows model agreement and uncertainty. It distinguishes from sibling tools like get_weather_forecast and compare_passes by specifying the unique resource and action.

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 for forecast reliability queries,' giving explicit guidance on when to use the tool. While it does not enumerate when not to use it, the context of sibling tools (e.g., get_weather_forecast) implies alternatives, and the guidance is clear enough.

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 no behavioral details beyond the optional parameters. For a read-only query tool, this is minimal additional 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?

Two sentences, no filler. The first sentence states the core purpose, the second adds context for optional parameters. Perfectly concise and front-loaded.

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 comparison tool with an output schema and 4 optional parameters, the description covers the essential usage. No critical gaps, though it could mention what the output includes (e.g., comparison table).

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?

Parameter descriptions in the schema cover 100% of parameters. The tool description adds value by explaining the use-case for tripDays and resortSlugs (seeing coverage and value comparison).

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 starts with 'Compare ski passes on price, resort coverage, and value,' which clearly states the verb (compare) and resource (ski passes). This distinguishes it from sibling tools like get_pass and find_pass_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?

The description explains when to use optional parameters: 'pass resortSlugs you plan to ski and tripDays to see which pass covers them and whether it beats buying window lift tickets.' This provides clear context, though it lacks explicit when-not-to-use 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, idempotentHint=true, and destructiveHint=false. The description adds that 'every value comes from the SnowSure conditions resolver/contract', providing data source context. However, it does not disclose behavioral traits like rate limits or auth needs. No contradiction 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 consists of two concise sentences. The first sentence states the core purpose and data source, while the second adds optional functionality. 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?

Given the tool's complexity (2 parameters, output schema exists), the description covers the core behavior and input constraints adequately. It could mention the output format, but the presence of an output schema mitigates this gap.

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 both parameters. The description adds high-level grouping ('across snow, terrain, and live conditions') but does not significantly enhance understanding beyond the schema's explicit list of dimensions.

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 verb 'compare', the resource 'resorts', and the scope '2–4 resorts side by side across snow, terrain, and live conditions'. It distinguishes from siblings like compare_forecasts and compare_passes by focusing on overall resort comparison.

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 comparing resorts across multiple dimensions but does not explicitly state when to use this tool versus alternatives like compare_forecasts or find_best_powder. No exclusions or prerequisites are mentioned.

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, so the tool is safe. The description adds transparency by stating the results are sorted by 24-hour snowfall and are real-time, complementing the 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?

The description is two sentences (25 words), front-loads the core purpose, and includes usage guidance without superfluous information. Every word 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?

Given the tool has optional parameters and an output schema (not shown but indicated), the description covers the essential context: what the tool does, how results are sorted, and when to use it. It could mention the dependency on current data, but 'right now' suffices.

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 100% description coverage, with each parameter already documented. The tool description does not add additional parameter meaning beyond what the schema provides, so 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 verb 'find' and resource 'resorts with the freshest powder snow', and specifies sorting by 24-hour snowfall. It distinguishes this tool from siblings like 'find_resorts_by_criteria' or 'get_snow_report' by focusing on immediate fresh snow queries.

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: for 'where is it snowing?' or 'fresh powder' queries. It does not exclude other scenarios or mention alternatives, but the usage context is clear and actionable.

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. The description adds context about generating flight-search links and gateway airports, which aligns with read-only behavior. No contradictions. Could mention rate limits or external dependencies, but overall sufficient.

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 crucial info front-loaded. No wasted words. Every sentence adds value: purpose, funnel context, parameter guidance.

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 rich annotations and expected output schema, the description covers purpose, parameters, and usage flow completely. It explains how to use the tool in the broader trip planning context, making it self-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 coverage is 100%, yet the description adds meaning: explains 'resort' as a slug resolvable via search_resorts, and clarifies 'origin' as optional IATA or city name. This goes beyond the schema's basic type/required info.

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: finding nearest gateway airports and flight-search links from a home airport. It uses a specific verb ('find') and resource ('flights to powder'), and differentiates from siblings like find_best_powder and book_lodging by explaining the funnel placement.

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 ('pair with find_best_powder / find_powder_trips ... → this → book_lodging'), and instructs how to resolve resort names using search_resorts. This provides clear context and 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?

Annotations already indicate idempotent, read-only behavior. Description adds value by specifying the return format (names + SnowSure slugs) and the optional nature of the region filter, without contradicting 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?

Two sentences, front-loaded with action, no filler. Every sentence provides useful 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?

Given the output schema exists and parameters are fully covered, the description is complete for this simple list tool. It explains the output purpose (slugs for get_resort) and optional filtering.

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. Description paraphrases region as optional filter, adding no additional 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?

Description clearly states the tool lists resorts on a ski pass with optional region filter, and distinguishes from sibling tools like get_resort (which receives slugs from this tool) and find_resorts_by_criteria (which searches by different criteria).

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 context for when to use (listing resorts on a pass) and mentions integration with get_resort, but does not explicitly state when not to use or enumerate alternatives among 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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and non-destructive. Description adds context about external booking links and that booking completes on LUXSKI, which is valuable beyond annotations. No 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?

Single well-structured paragraph front-loading the main purpose. Every sentence adds value, though slightly verbose with the last sentence about booking links. Still concise overall.

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 output schema present, description does not need to explain return values. Parameter count is 3, all optional with full schema coverage. The description covers use cases, optional filters, and outcome (booking links). Adequately complete for the complexity.

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 is 3. Description adds application-level context for each parameter, e.g., 'vibe filter shows only hotels handpicked into that tier', enhancing understanding beyond the schema's enum list.

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 tool ranks resorts by 14-day forecast and returns handpicked luxury ski hotels for booking. It uses specific verbs and resources, distinguishing it from siblings like find_best_powder (which may rank without booking) and book_lodging (which focuses on booking only).

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?

Explicitly provides usage examples ('Use for...') and mentions optional vibe filter. However, it does not explicitly state when not to use or compare to alternatives beyond the provided examples, which is acceptable given the 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?

Annotations already declare readOnlyHint=true and idempotentHint=true, so the description does not need to restate safety. The description adds behavioral context by specifying it is for 'advanced filtering' and lists available criteria. It does not contradict annotations and provides useful context beyond them.

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 long, front-loaded with the action and key criteria, and no extraneous information. Every sentence serves a 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 7 optional parameters and an output schema (not shown), the description is adequate. It covers the main filtering purpose. However, it could mention that it returns a list of resorts (implied) and that the limit parameter controls result size, but those are in the schema.

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 the baseline is 3. The description mentions criteria categories (snow depth, elevation, etc.) but does not add deeper semantic meaning beyond what the schema already provides in each parameter's description.

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 verb 'Find', the resource 'resorts', and lists specific criteria (minimum snow depth, elevation, runs, SnowSure rating). It also positions it for 'trip planning'. However, it does not explicitly differentiate from sibling tools like 'search_resorts' or 'compare_resorts', which perform similar functions.

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 'trip planning' and mentions 'Advanced filtering', but it does not provide explicit guidance on when to use this tool versus alternatives. No when-not or alternative tools are mentioned, which could lead to confusion among the many 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?

Annotations already indicate the tool is read-only, idempotent, and non-destructive. The description adds valuable behavioral context: the data is relayed from an official service, includes the issuer and link, and returns 'no bulletin' when unavailable. This goes beyond the 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?

The description is two concise sentences, front-loading the core functionality and then covering the edge case and a critical warning. Every sentence adds value, and there is no redundancy or filler.

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 simplicity (one parameter, no enums, output schema present), the description covers the main behavior, the specific return case for unavailable data, and a usage warning. It is fully adequate for an agent to correctly invoke the tool.

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 100% description coverage for the single required parameter 'slug', with an example. The tool description does not mention the parameter, but the schema already provides sufficient semantics. A score of 3 is appropriate as the description adds no further meaning.

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 the current avalanche danger bulletin for a resort’s forecast zone, including the issuer and link. It specifies supported regions (US, Canada, Switzerland in v1) and handles the 'no bulletin' case. While it does not explicitly differentiate among siblings, the purpose is distinct and well-defined.

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 a caution that the tool is not a substitute for official bulletins or avalanche training, implying appropriate use. However, it does not explicitly state when to use this tool versus alternatives like get_snow_report or get_operating_risk, leaving usage guidance somewhat implied.

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, destructiveHint=false. The description adds that it returns a 'table of member ski areas', which is useful but not extensive. No contradictions, and the description provides additional context 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?

Two efficient sentences: first states purpose, second gives usage boundaries. No fluff, front-loaded with key 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?

Given the tool's simplicity, presence of output schema, and comprehensive annotations, the description covers all necessary context. Usage guidelines, behavioral traits, and parameter meanings are adequately addressed.

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 both parameters described. The description adds minimal extra semantics: it mentions an alias example ('hakuba valley') already covered in the slug parameter description. Baseline 3 is appropriate as the schema carries the load.

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's a 'Multi-mountain destination hub' with a table of member ski areas, distinguishing it from siblings by specifying it is NOT for photo gallery or resort guide cards. The verb+resource is specific and 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?

Explicitly states when to use ('Use ONLY when the user names the hub itself') and when not to, providing alternatives (→ get_resort_photos, → get_resort_info). This gives clear decision criteria.

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, destructiveHint. Description adds behavioral context: 'skip simple leaderboards' for intelligence type, and explains scope options. No contradictions.

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, front-loaded sentences. Every sentence adds value. No redundancy or filler.

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?

Output schema exists, annotations cover safety. Description mentions typical analytical questions, filtering options, and result types. Complete for a read-only insights tool with good parameter documentation.

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 enums and descriptions. Description adds value: explains 'snapshot vs global' and 'intelligence skips leaderboards'. Baseline 3, plus extra clarity earns a 4.

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?

Specific verb+resource: 'Get categorized SnowSure intelligence insights'. Distinguishes from sibling tools like get_snow_report by focusing on insights beyond snow totals. Examples of questions it answers further clarify purpose.

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?

Clearly states when to use (answers analytical questions) and gives filtering guidance (category, insightType). Recommends insightType=intelligence. Lacks explicit when-not directions, but context is sufficient.

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, idempotentHint=true, destructiveHint=false, so the description adds little beyond acknowledging a public API. No behavioral traits beyond annotations are disclosed, but no contradiction either.

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, each serving a purpose: verb+resource, example datasets, and usage guideline. Front-loaded efficiently, though slightly verbose in the list of datasets.

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 complexity of 10 parameters with 100% schema coverage and an output schema present, the description is complete enough. It includes a recommended starting point (dataset=catalog) and context for when to use alternatives.

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 description adds minimal parameter-specific information beyond what is already in the input schema. 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?

Clearly states it fetches SnowSure-unique ML/AI trend datasets from a public REST API, listing specific dataset types (powder-day leaders, bluebird predictions, etc.) and explicitly distinguishes from sibling tool get_insights.

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 guidance: 'Start with dataset=catalog' and 'Prefer get_insights for narrative intelligence cards; use this for raw rankings and time series.' Clearly states when to use this tool vs alternative.

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 read-only, idempotent, non-destructive. Description adds valuable context: requires OAuth, ranking by freshness. No contradictions.

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 concise sentences, front-loaded with purpose, then authentication. Every sentence adds value.

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 purpose, ordering, auth requirement. Could mention edge cases (e.g., no saved resorts), but output schema likely handles return values. Fairly complete for a simple tool.

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 baseline is 4. Description does not need to add parameter info; it's already clear from empty 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 returns a personalized snow report for the user's saved resorts, with live conditions ranked by freshness. It distinguishes from siblings like 'get_snow_report' which is generic.

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?

Explicitly notes OAuth token requirement. Provides clear context for when to use (authenticated users with saved resorts), but does not explicitly mention when not to use or compare with alternatives like 'list_saved_resorts'.

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. The description adds valuable context: it uses Open-Meteo forecast, factors in specific weather conditions (wind, visibility, cold, heavy snow), and emphasizes it's not the resort's official decision. No contradictions.

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: a catchy question followed by a clear explanation, then a caution. Every part adds value 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 presence of an output schema, the description does not need to detail return values. It covers time horizon (48 hours), data source, and limitations. It could mention if any authentication is needed, but annotations don't require it. Compete enough for a simple tool.

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 description 'Resort slug'. The tool description does not add additional parameter-level information beyond what the schema provides, but it does indirectly clarify the parameter's role in the overall tool purpose. 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?

The description clearly states the tool provides a 48-hour operating-risk estimate based on weather factors, distinguishing it from sibling tools like get_weather_forecast (raw weather) or get_snow_report (current conditions). The verb 'get' and resource 'operating risk' are specific.

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 advises that the output is modeled guidance, not the resort's decision, and instructs users to always check live lift status. While it doesn't name sibling tools as alternatives, the context of when to use and when not to rely is 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 indicate readOnlyHint=true and destructiveHint=false. The description adds value by listing the specific fields returned (operator, pricing tiers, etc.), providing behavioral context beyond annotations. No contradictions.

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 that is front-loaded with the main purpose and includes a list of details. Every part is meaningful, with 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?

Given the presence of an output schema, the description does not need to explain return values. It clearly states what the tool does and what specific details are included. For a simple tool with one parameter and rich annotations, this is fully 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 100%, so the schema already documents the single parameter 'passId' with a description. The description adds examples (e.g., 'epic-pass') that are helpful but not essential. Baseline 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 retrieves details for a multi-resort ski pass and lists specific fields (operator, pricing tiers, destination count, regions, buy link). This is a specific verb+resource structure that distinguishes it from sibling tools like 'compare_passes' or 'find_pass_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?

While the description implies usage for getting details of a specific pass, it provides no explicit guidance on when to use this tool versus alternatives such as 'compare_passes' or 'find_pass_resorts'. No exclusions or context 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 declare readOnlyHint=true and idempotentHint=true, indicating no side effects. Description adds 'statistics and top resorts' but no behavioral details beyond what annotations provide. The description does not contradict 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?

Two short, front-loaded sentences convey purpose and usage without extraneous words. Every sentence adds value.

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 simplicity (two optional parameters, output schema present), the description sufficiently covers purpose and parameter usage. It does not need to explain return values because an output schema exists.

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 parameter descriptions. The description adds extra context: 'Provide region or country (at least one). Region is preferred for multi-country areas.' This clarifies the relationship and usage beyond schema, though schema already describes parameters individually.

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 the tool retrieves a summary of snow conditions across a region or country, including statistics and top resorts. This specific verb-resource combination distinguishes it from sibling tools that focus on single resorts or specific reports.

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?

Description provides clear guidance on parameter usage: 'Provide region or country (at least one). Region is preferred for multi-country areas.' This helps the agent decide when to use each parameter but does not explicitly compare to sibling tools or state when not to use 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=true, idempotentHint=true, destructiveHint=false. The description adds behavioral context by explaining that the card parameter determines the interactive UI output, and provides examples of what each card returns. No contradiction 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 thorough but slightly verbose. Each sentence adds value, but the list of card mappings could be more concise. Still, it is well-structured with clear sections.

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 presence of an output schema, the description does not need to detail return values. It covers all card types, provides examples, and includes helpful usage hints. It adequately completes the context for agent selection and invocation.

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 both parameters described. The description adds natural language mappings for enum values (e.g., card=guide for resort info) and example slugs, providing 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 'Single-resort data' (verb+resource) and distinguishes itself from siblings like get_resort_info and get_resort_photos. It explains the specific card parameter that picks the UI, making the tool's purpose 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 provides explicit mappings from user intent to card values (e.g., 'Resort guide' → card=guide, 'Conditions/forecast' → card=snow) and recommends preferring more specific sibling tools when available. This guides the agent on when to use this tool vs. 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?

Annotations already declare readOnly and idempotent hints. Description adds context on the data returned (editorial description, carousel) but does not disclose additional behavioral traits 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?

The description is well-structured with a data list, required context, examples, and a do-not-use note. Every sentence is purposeful.

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 one parameter and output schema present, the description fully covers the tool's purpose, usage, and differentiation. No 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 100% and the description includes example slug values, but does not add new meaning beyond the schema description. 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?

The description clearly states it provides an interactive resort guide card with specific data (elevation, vertical, lifts, etc.) and distinguishes from the sibling tool get_resort that shows snow conditions. It gives explicit verbs and examples.

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?

Explicitly states when it is required with a list of user intents and provides example queries. Also says 'Do NOT use get_resort' for clear 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds behavioral context (interactive carousel, official Sanity gallery), which is useful beyond the structured fields. No contradictions.

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 concise sentences with bold highlighting of key phrases (REQUIRED, Never, Do NOT). Every sentence adds value; 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?

With an output schema present and full annotations, the description covers purpose, usage context, and exclusions completely. It provides all necessary information for an AI 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% and the slug parameter description is adequate. The description does not add additional parameter detail, but the schema already sufficiently documents the parameter; 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?

The description clearly states the tool provides an interactive photo gallery carousel with official resort photos, lists triggering keywords, and explicitly distinguishes from sibling tools like get_destination, get_resort_info, and ask_snowdata.

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?

Explicitly states when this tool is required (for photos, pictures, images, gallery, or specific photo requests) and provides clear prohibitions against using web search, inline images, or other tools for photo requests.

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 read-only and idempotent behavior. The description adds valuable context: returns 'no road data' outside covered areas, links to official DOT maps, and notes the resort's road status is authoritative. No contradictions.

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 with no waste. It efficiently conveys purpose, sources, coverage, and behavior. Every sentence adds value.

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 simple input, high schema coverage, and presence of output schema, the description adequately explains data sources, coverage, and edge cases. It does not detail output fields but the output schema likely covers 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?

The parameter 'slug' is fully described in the schema (100% coverage). The description adds no additional meaning beyond stating it refers to a resort, so baseline score 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 clearly states the tool retrieves driving access conditions for a resort, specifying chain-control, mountain-pass, and road-surface conditions from multiple state DOTs. It distinguishes from siblings like get_road_cameras and get_road_weather by focusing on access conditions.

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 driving access queries but does not explicitly state when to use this tool versus alternatives. It provides no guidance on exclusions or preferred contexts among 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?

Annotations already indicate readOnlyHint, idempotentHint, and destructiveHint. The description adds useful detail: it returns 'no road cameras' outside the covered area, each camera includes a live image URL, and the geographic scope (California, Washington, Utah). This goes beyond annotations without contradicting them.

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, efficiently conveying purpose, coverage, output behavior, and distinction from alternatives. Every sentence earns its place with no fluff or repetition.

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 presence of an output schema, the description adequately covers return values (live image URL, 'no road cameras' outside area) and scope. It is mostly complete for a simple lookup tool, though it could mention potential delays in image updates or rate limits.

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 parameter 'slug' described as 'Resort slug'. The tool description mentions 'near a resort', which aligns but does not add significant meaning beyond the schema. No additional constraints or formatting are provided, so the description adds minimal value for parameter understanding.

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 live roadside DOT/CCTV camera stills near a resort, specifying the states and agencies (Caltrans, WSDOT, UDOT). It explicitly distinguishes from resort webcams, making the purpose unambiguous and differentiating it from sibling tools like get_webcam_status.

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 clear context that this tool is for live road conditions near a resort and is distinct from resort webcams, implying when to use it. However, it does not explicitly state when not to use it or list specific alternatives, leaving some ambiguity for cases where users might want forecasts or other road data.

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 readOnly and idempotent. The description adds context: returns 'no road weather' outside covered area, specifies data sources (CDOT, WSDOT, UDOT), and clarifies it's sensor data distinct from modeled, enhancing transparency 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?

Two concise sentences front-load the essential purpose and key details (data sources, distinction from modeled tools) with no redundant words. Every sentence provides value.

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 simple input (one parameter), full schema coverage, existing annotations, and output schema (present), the description is complete. It covers limitations (coverage area) and data provenance, sufficient for an agent to select and 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 input schema has 100% coverage for the single 'slug' parameter with description 'Resort slug'. The description does not add additional meaning or constraints beyond the schema, so 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?

The description clearly states it provides measured roadside weather data near a resort, listing specific measurements (temperature, visibility, wind, precipitation) and distinguishing it from the modeled get_operating_risk.

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 suggests use when measured road sensor data is needed rather than modeled risk, but does not explicitly state when to use this tool versus alternatives or provide exclusion criteria.

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. The description adds that it returns only scheduled/confirmed openings for that date, not currently-open resorts, which is useful context. However, it does not detail output schema or pagination, but output schema exists.

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 clear purpose, examples, and sibling differentiation. While it is slightly long, every sentence serves a purpose. Front-loaded with the core function.

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 4 optional parameters, output schema, and complete annotations, the description fully covers scope, constraints, and alternatives, making it highly 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 description coverage is 100%, so baseline is 3. The description does not add new meaning about parameters beyond the schema, but usage examples implicitly show how date works. It meets the baseline.

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 resorts whose season opening date matches a specific day, with examples like 'what opens today?' and explicitly distinguishes from siblings like get_southern_hemisphere_report and ask_snowdata.

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?

Explicitly states when to prefer this tool over get_southern_hemisphere_report for opening-day questions, and directs historical-norm queries to ask_snowdata, providing clear when-to-use and when-not-to-use 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 indicate readOnlyHint=true, idempotentHint=true, destructiveHint=false. Description adds behavioral details on returned data (season totals, averages) but doesn't disclose additional traits like authentication needs or rate limits.

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 of 20 words, front-loaded with key information, no unnecessary words. Every phrase 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?

Complexity is low: one required parameter, read-only, idempotent, with output schema present. Description sufficiently covers what the tool does without needing to document return values.

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% for the only parameter 'slug'. Description mentions 'for a resort' matching the slug role, but adds no new meaning beyond the schema's 'Resort slug' description.

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 verb 'Get', resource 'historical snowfall data', and specifies details (season totals, comparisons, best months). It distinguishes from siblings like 'get_snow_report' (current conditions) and 'get_ml_trends' (trends).

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?

Description implies usage for historical context but lacks explicit guidance on when to use vs alternatives like 'get_snow_report' or 'find_best_powder'. No when-not or exclusions 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, idempotentHint=true, destructiveHint=false. The description adds that the tool returns top-ranked resorts sorted by various criteria, which is consistent and provides some additional behavioral context beyond annotations. No contradictions.

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, consisting of two short sentences that front-load the purpose and usage. Every sentence adds value without any unnecessary 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's simplicity (optional params, enums, read-only, with output schema), the description adequately covers the functionality. It provides example queries and mentions sorting options. The output schema handles return values, so no further detail is needed.

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 the baseline is 3. The description mentions sorting by SnowSure score, forecast, etc., which aligns with the schema. It does not add significant new meaning beyond what the schema descriptions provide, so a 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 verb 'Get', the resource 'global snow report', and what it returns (resorts sorted by SnowSure score, forecast, etc.). It also provides example queries. However, it does not explicitly differentiate from sibling tools like 'get_my_snow_report' or 'compare_resorts', though the global scope is implied.

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 use cases: 'where has the best snow?' or 'top ski resorts right now' queries. This provides clear context for when to use the tool, but it does not mention when not to use it or identify alternative tools for specific 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=true and idempotentHint=true, so the description adds the detail that it prefers operator-verified data when available, which provides extra behavioral context 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?

The description is extremely concise with no wasted words, front-loading the core purpose, then examples, then usage guidelines. Every sentence serves a 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 simplicity and the presence of an output schema (indicated in context), the description covers purpose, usage, region, and time period completely, answering typical agent questions.

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%, and the description does not add significant meaning beyond what the schema already documents for each parameter. 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?

Description clearly states the tool retrieves snow conditions for Southern Hemisphere ski resorts (Australia, New Zealand, Argentina, Chile) currently in season, and distinguishes itself from get_season_openings by explicitly excluding specific opening date queries.

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 for June–October SH ski queries' and instructs not to use for specific opening dates, directing to get_season_openings instead, providing clear when-to-use and when-not-to-use 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, destructiveHint=false, and idempotentHint=true. The description adds value by specifying the forecast contents (temp, snow, wind, conditions) and the 14-day range. No contradictions. It could mention data freshness or rate limits, but the annotations cover the behavioral safety profile.

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, clear, front-loaded sentence with 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?

The tool has low complexity with only 2 parameters and an output schema exists. The description covers what the tool returns and the scope. It is complete for an agent to understand the tool's purpose and 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 coverage is 100%, with both parameters described. The description does not add meaning beyond the schema; it mentions '14 days' but the schema already has max:14 for the days parameter. 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?

The description clearly states the verb 'Get' and resource 'weather forecast for a resort', specifying the details (temperature, snowfall, wind, conditions) and scope (each of the next 14 days). It distinguishes from sibling tools like get_snow_report and compare_forecasts.

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 obtaining a detailed forecast but does not provide explicit when-to-use guidance or alternatives. Given the large set of sibling tools, some exclusion statements would be beneficial, but the purpose is clear enough.

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 readOnly, idempotent, non-destructive behavior. The description adds value by specifying it retrieves 'links and status' for visual conditions, confirming it's a safe read operation. No contradictions.

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, well-structured sentence that front-loads the purpose and includes example queries. 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 simple read tool with one parameter, output schema present, and comprehensive annotations, the description is complete. It covers the tool's purpose and usage scenarios adequately.

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 one parameter 'slug' with 100% schema coverage. The description does not add extra meaning beyond the schema's 'Resort slug' description. Baseline 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 retrieves live webcam links and status for a resort, explicitly mentioning use cases like 'show me the webcam' and named-cam lookups. It distinctly separates from sibling tools like get_resort_photos.

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 clear context for when to use (answering webcam-related queries) but does not explicitly state when not to use or list alternative tools. The sibling list implies alternatives, but explicit guidance would improve.

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 provide readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds the behavioral context of requiring an OAuth token, which is not in 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?

A single sentence that states the action and a key requirement. No wasted words; front-loaded with the 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?

The tool is simple with no parameters, and an output schema exists. The description covers the purpose and a key behavioral context, making it fully complete for an AI agent to decide and invoke.

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?

There are no parameters, so the description does not need to add information beyond the schema. It is appropriately concise and adds no redundant parameter details.

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 a specific verb and resource: 'List the signed-in user's alert subscriptions.' It clearly distinguishes this from sibling tools like 'subscribe_alerts' and 'unsubscribe_alerts'.

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 a key prerequisite: 'Requires a SnowSure user access token (OAuth).' While it doesn't explicitly say when not to use this tool, the context with siblings makes it clear that this is for listing existing subscriptions.

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, so the safety profile is clear. The description adds value by characterizing the data as 'lighter than raw leaderboards' and 'retrospective and verification-backed,' which informs the agent about data quality and performance.

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 short sentences. The first states the purpose with a list of categories, and the second provides usage guidance and context. Every word earns its place with no waste.

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 zero parameters, a simple output (list of categories), and the presence of an output schema, the description is fully complete. It covers what the tool does, lists the categories, and explains when to use it relative to a sibling.

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 zero parameters and 100% schema description coverage, so the baseline is 4. The description does not need to add parameter information since there are none.

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 lists SnowSure insight categories and enumerates them explicitly (live conditions, current season, etc.). It distinguishes itself from sibling tools like get_insights by noting it is 'lighter' and 'retrospective and verification-backed cards.'

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 advises using this tool before get_insights to choose a category filter, providing clear usage context. However, it does not explicitly state when not to use it or mention alternatives beyond get_insights.

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 read-only, idempotent, non-destructive behavior. The description adds value by disclosing the authorization error response and a hint for the agent to connect, which is 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 concise with two sentences, no superfluous words. It front-loads the purpose and adds a critical behavioral detail in the second sentence.

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 parameters and an output schema present, the description covers all needed context: the resource being listed, the auth requirement, and a behavioral note. No 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?

The tool has no parameters, and schema coverage is 100%. The description does not need to elaborate on parameters beyond the implicit context of 'saved resorts'.

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 verb 'list' and resource 'signed-in user's saved resorts'. It distinguishes from sibling tools like 'save_resort' and 'remove_saved_resort' by specifying the action and scope.

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 context for when to use the tool (listing saved resorts) and highlights a prerequisite (OAuth token). However, it does not explicitly state when not to use it or mention 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?

Annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds behavioral details about the planning algorithm (nearest-neighbour, minimal backtracking, conditions integration) beyond annotations, providing useful transparency 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?

The description is a single, well-structured paragraph that front-loads the main purpose and immediately lists the key actions. Every sentence adds value, and no superfluous information is present.

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, the presence of an output schema (eliminating need to describe returns), and comprehensive annotations, the description fully covers the tool's behavior—resort selection, route optimization, day allocation, driving estimates, and live conditions.

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 67% (two of three parameters have descriptions). The description merely repeats parameter names and required status without adding new semantic details. It adds no additional meaning beyond what the schema already provides.

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 plans a multi-stop ski road trip, detailing specific actions like picking top-scoring resorts, ordering via nearest-neighbour, allocating days, estimating driving legs, and incorporating conditions. It distinguishes itself from the sibling 'plan_ski_trip' by emphasizing multi-stop and driving.

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 specifies usage for multi-stop ski road trips but does not explicitly state when not to use it or contrast with similar tools like 'find_powder_trips' or 'plan_ski_trip'. However, the context is clear enough for an agent to infer appropriate 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, so the agent knows this is a safe read operation. The description adds no behavioral traits beyond what is inferred from the schema (e.g., no mention of rate limits, response size, or any side effects). Since annotations cover the safety profile, the description contributes minimal additional 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 two sentences, front-loading the primary action and mentioning key inputs. No redundant words. Perfectly concise for a tool with well-documented parameters.

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 tool does not need to explain return values. The description covers the high-level purpose. Given the broad input (all fields optional) and many siblings, it is adequately complete for a planning tool. Missing could be explicit mention of scope (e.g., top N resorts) but not critical.

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 each parameter having clear descriptions and enums. The input schema description adds context about optionality. The tool description does not add further parameter meaning, so 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?

The description clearly states the tool provides ski trip recommendations based on dates, preferences, and conditions, and suggests best resorts for a time period. The verb 'get' and resource 'recommendations' are specific. However, it does not explicitly differentiate from sibling tools like 'find_best_powder' or 'compare_resorts', so it gets 4 rather than 5.

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 guidance on when to use this tool versus alternatives. It does not state when not to use it or mention any prerequisites. This is a significant gap given 39 sibling tools with overlapping functionality.

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 destructiveHint=true and idempotentHint=true. The description adds the authentication requirement, which is useful beyond the annotations, and clarifies it acts on the signed-in user's list.

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 concise, front-loaded sentences with no extraneous information. Every word 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?

For a simple, single-parameter tool with an output schema and complete annotations, the description covers purpose, authentication, and target user context without any 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 100% with a single parameter 'slug' described in the schema. The description adds no further meaning to the parameter beyond what the schema provides, so baseline score 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 action ('Remove a resort') and the target context ('from the signed-in user's saved list'), distinguishing it from siblings like 'save_resort' and 'list_saved_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 specifies a prerequisite ('Requires a SnowSure user access token (OAuth)') but does not explicitly state when to use this tool versus alternatives like 'save_resort' or 'unsubscribe_alerts'.

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?

Description adds non-obvious traits (requires OAuth, slug validity) beyond annotations which already indicate idempotency and non-destructiveness. No 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 concise sentences with no wasted words, front-loading 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?

Given output schema existence, description adequately covers purpose, prerequisites, and constraints. No 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 covers 100% of parameters with clear description and example ('jackson-hole'). Description reinforces constraint that slug must be real, adding value.

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 uses specific verb 'save' and resource 'resort to favorites', clearly distinguishing it from siblings like 'list_saved_resorts' and 'remove_saved_resort'.

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?

Specifies prerequisites (OAuth token, real slug) but does not mention when not to use or alternative tools like checking if already saved.

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, idempotentHint=true, and destructiveHint=false. The description adds only that it 'returns matching resorts with basic conditions,' but does not disclose additional behavioral traits such as pagination behavior, rate limits, or how it handles no results.

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, consisting of two sentences with no unnecessary words. It is front-loaded with the core purpose and includes example queries, making it 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?

Given that an output schema exists and all parameters are documented in the input schema, the description covers the essential search behavior. It lacks details on handling edge cases like no results or invalid queries, but overall it is sufficient for a search tool.

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 all three parameters (limit, query, country) described in the schema. The description does not add extra parameter semantics beyond what the schema provides, so 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 searches for ski resorts by name, country, or region and returns matching resorts with basic conditions. It provides specific use case examples, effectively differentiating from siblings like get_resort or get_resort_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 includes explicit usage examples ('find resorts in [location]' or 'search [name]'), guiding appropriate queries. However, it does not mention when not to use this tool or suggest alternatives among the many 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?

Annotations indicate readOnlyHint=false (write operation) and destructiveHint=false. The description adds authentication requirements (SnowSure OAuth token). It lacks details on whether subscribing multiple times to the same alert is idempotent, but overall is 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 two sentences, front-loaded with purpose, but contains dense information. Every sentence adds value, though slightly structured 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 5 parameters, 1 required, and an output schema (not shown), the description covers all necessary aspects: auth, alert types, parameter explanations. Sibling tools are handled via 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 100%, but the description adds significant value: it explains the meaning of each type, provides default values for thresholdCm (15 for powder, 30 for forecast) and windowDays (1-14, default 14), which are not in 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 action (subscribe) and the resource (snow alerts), with explicit types (powder, forecast, opening, bluebird). It distinguishes from sibling tools like unsubscribe_alerts and list_alerts.

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 explains when to use each alert type (e.g., powder for fresh snow, forecast for proactive watcher). It does not explicitly contrast with other tools but provides sufficient context for selecting the correct alert type.

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 destructiveHint=true, so the description adds value by specifying the OAuth requirement. No contradictions.

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, no superfluous information, highly 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?

For a simple tool with one parameter and an output schema, the description provides the essential context: action, auth requirement, and source of the id.

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% for the single parameter. The description adds context by explaining that the id comes from list_alerts, which is beyond the schema's description.

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 action ('Remove'), resource ('alert subscriptions'), and provides a reference to list_alerts for obtaining the id. It distinguishes itself from sibling tools like subscribe_alerts and list_alerts.

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 mentions the need for a SnowSure user access token and implies the id comes from list_alerts, but does not explicitly state when to use this tool versus alternatives or exclusions.

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