Greetwell Experiences

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

With no annotations provided, the description carries the full disclosure burden. It usefully indicates 'Read-only' nature (safety hint) and specifies the date format (YYYY-MM-DD), but omits error handling (invalid product_id, past dates), rate limits, or whether availability is real-time vs cached.

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?

Extremely compact single sentence (9 words). Front-loads 'Read-only' as a behavioral hint and parenthetically includes the date format. However, brevity comes at the cost of leaving parameters undocumented given zero schema coverage.

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?

Acceptable for a read-only tool with an output schema (return values need not be described), but insufficient given 0% input schema coverage. The description should explain the party_size parameter and clarify that product_id identifies the activity, especially since the tool name uses 'activity' while the parameter is 'product_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 has 0% description coverage, so the description must compensate. It mentions 'date' with required format and implies 'activity' maps to product_id, but completely omits explanation of 'party_size' (optional, defaults to null) and what effect it has on availability calculations.

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?

States the core action (retrieving availability) and resource (activity on a date) clearly. However, it does not explicitly differentiate from sibling 'get_activity_details' which might also return availability information, nor does it clarify what 'availability' means (time slots, capacity, boolean, etc.).

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 no guidance on when to use this tool versus siblings like 'search_activities' or 'get_activity_details'. No mention of prerequisites (e.g., needing a product_id from search) or when to include optional parameters like party_size.

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

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

With no annotations provided, the description carries the full disclosure burden. It explicitly states 'Read-only' (critical safety information) and reveals key response contents ('booking_link', 'item_card') beyond what structured fields provide, though it omits error handling or rate limit details.

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 with zero waste: first sentence front-loads the purpose and safety characteristic ('Read-only'), second sentence adds value by previewing useful response fields. 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 read-only getter with one parameter and an existing output schema, the description is largely complete. It covers safety, scope, and highlights valuable output fields, though it would benefit from one sentence clarifying the product_id input.

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 0% (product_id has no description). While 'single activity/product' semantically implies the parameter identifies one specific item, the description fails to explicitly name or describe the product_id parameter, providing insufficient compensation for the undocumented 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 uses a specific verb+resource pattern ('Read-only details for a single activity/product') that clearly distinguishes from sibling tools: 'single' differentiates from search_activities (plural/browsing), and 'details' differentiates from get_activity_availability (likely returns schedule/availability data).

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 term 'single activity/product' implies usage when a specific product is identified (vs. browsing/searching), providing implicit context for when to use this tool. However, it lacks explicit contrast with siblings like 'use search_activities to find products, then use this tool to get details'.

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

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

With no annotations provided, the description carries the full burden of disclosure. It successfully indicates the read-only safety profile and describes the output structure (includes `booking_link` and `item_card`), but omits behavioral details about the ranking algorithm, filtering interactions, or error conditions.

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 model of efficiency: two sentences with zero waste, front-loaded with the operation type and core dependency, followed by output structure details. Every word 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 output schema exists, the description appropriately references key output fields. However, for a tool with 9 parameters and zero schema documentation, the description is incomplete as it omits guidance on optional filters (party composition, radius, temporal constraints) that significantly affect results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage across 9 parameters, the description only adds semantic context for the required product_id parameter ('source product_id', 'anchored to'). It completely fails to explain the 8 optional filtering parameters (date, location, time_slot, party_size, has_children, includes_children, radius_miles, max_recommendations) despite their complex anyOf types.

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 identifies the action ('Read-only ranked'), the resource ('complementary activities'), and the required anchor ('source product_id'). It effectively distinguishes this from sibling search tools by emphasizing the 'complementary' relationship to an existing product.

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 a product_id is required ('anchored to a source product_id'), it provides no explicit guidance on when to use this tool versus siblings like search_activities or get_activity_details, nor does it mention prerequisites or exclusions.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure, stating the operation is 'Read-only' and detailing output fields (booking_link, item_card). However, it omits pagination behavior, rate limits, error handling for empty results, and the dual string/object nature of the location parameter.

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 two-sentence description is efficiently structured with no redundant words, front-loading the core purpose in the first sentence and output details in the second. However, given the zero schema coverage across eight parameters, this extreme brevity contributes to under-specification rather than demonstrating appropriate completeness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite mentioning the output structure (booking_link, item_card), the description inadequately covers the tool's complexity—eight parameters with zero schema descriptions—leaving five parameters completely undocumented and providing no usage context beyond basic search functionality.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage across eight parameters, the description must compensate heavily but only references three parameters (location, query, date) and fails to explain critical filters like party_size, has_children, and includes_children. It also does not clarify that location accepts either a string or a coordinate object, leaving significant semantic gaps.

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 states 'Read-only search for activities by location/query/date,' providing a specific verb (search), resource (activities), and scope (location/query/date filters). It distinguishes this from sibling get_* tools by implying broad discovery versus specific retrieval, though it does not explicitly contrast with get_complementary_recommendation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no explicit guidance on when to select this tool over siblings like get_complementary_recommendation or get_activity_details, nor does it state prerequisites or conditions for use. While 'Read-only' implies the tool is for querying rather than booking, it lacks explicit when/when-not guidance.

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