waysway

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

With no annotations, the description carries the full burden. It mentions 'live' pricing and the prerequisite, which provides some behavioral context, but it does not disclose whether the operation is read-only, what happens if the prerequisite isn't met, or any side effects. It gives minimal but non-zero transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise and front-loaded with the main purpose, followed by the requirement. Every sentence earns its place. It loses one point because it is so brief that it omits essential parameter context, but as a concise description, it is well-structured.

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

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

The tool has 3 parameters, a prerequisite, and no annotations, yet the description provides no guidance on how to identify the hotel or interpret the session context. While an output schema exists, the description does not leverage it or explain the hotel selection mechanism, leaving the description incomplete for effective tool 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 description coverage is 0%, and the description does not explain any parameters. The phrase 'previously recommended hotel' hints that hotel_index might refer to a position in a recommendation list, but it does not clarify the relationship between hotel_index and hotel_code_or_name or when to use each. The description fails to compensate for the lack of schema documentation.

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 ('Check live stay price') and the specific resource ('previously recommended hotel'), which distinguishes it from general search tools. However, it does not explicitly name alternatives like get_booking_offers, so it is clear but not fully differentiated from siblings.

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 requirement 'update_stay_dates must already have been called' provides a necessary prerequisite, but it does not explain when to prefer this tool over alternatives or give broader context on when it is appropriate. This is useful but incomplete 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?

With no annotations, the description alone must disclose behavioral traits. It indicates that the session is cleared, but does not mention irreversibility, side effects on related data, or permission requirements. For a destructive operation, this is a significant omission.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single short sentence, which is concise, but it trades away needed detail. It is not a tautology, yet it provides only a minimal label-like statement and lacks structured information about parameters or effects.

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?

Although the tool has only one parameter and an output schema, the description fails to explain the parameter's role, the consequences of the action, or when to use the tool. This leaves the agent without enough context to invoke it safely or 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 defines one required parameter, session_id, with no description. The tool description does not mention this parameter or explain how it affects the clearing action, so there is no compensation for the 0% schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a clear verb 'clear' and identifies the resource as 'the entire session', making the core action understandable. While there are sibling session-management tools, none explicitly clear a session, so it is adequately distinguished.

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 gives no guidance on when this tool should be used, what prerequisites exist, or how it relates to alternatives like start_session or get_session_state. It merely states the action without context.

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

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

No annotations are provided, so the description carries the full burden for behavioral disclosure. It only says 'lightweight fallback' and 'for debugging', but does not explain what the extraction does internally, potential limitations, failure modes, or side effects. Given the lack of annotation support, this is insufficient.

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, using just a few lines and bullet points. It front-loads the core purpose and efficiently conveys the critical distinction from the preferred path. No filler or 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?

The tool has one simple parameter and an output schema, so return values are covered. The description provides strong usage context and alternatives. However, it lacks behavioral details like error handling, edge cases, or what happens when extraction fails. For a fallback tool, this leaves some gaps, making it minimally adequate.

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 schema has one 'text' parameter with 0% description coverage. The description says 'raw text', which adds minimal meaning beyond the parameter name. It doesn't specify expected input format, content type, length limits, or examples. With no schema descriptions, the description should compensate but fails to provide substantial parameter guidance.

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 'lightweight fallback extraction from raw text', which identifies the verb (extract) and resource (user profile). It also distinguishes itself from the preferred path by explicitly naming update_user_profile_from_model as the production alternative, making the purpose specific and differentiated.

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 this tool is 'mainly for debugging and fallback use' and 'NOT the preferred production path'. It goes further by describing the preferred path step-by-step, naming the alternative function. This provides 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?

No annotations are provided, so the description must carry the full burden. It reveals key prerequisites but does not disclose whether the operation has side effects, requires authentication, or how it errors if prerequisites are unmet. The 'get' verb implies a read, but the description is not richly 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 concise and well-structured: a clear one-line purpose followed by compact bullet requirements. Every sentence earns its place with no 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?

With 5 parameters, a required session_id, and 0% parameter coverage in the description, the tool definition is incomplete for correct invocation. It provides prerequisites but not operational detail on how to select the hotel or limit offers. The output schema covers returns, but input usage is under-specified.

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 schema has 5 parameters with 0% description coverage. The description only hints that the hotel should come from previous search results but does not explain hotel_index, hotel_code_or_name, limit, preferred_room_name, or session_id. This fails to compensate for the missing schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description starts with a specific verb+resource: 'Get available hotel offers for the current session dates.' It clearly states the scope (session dates) and distinguishes from get_hotel_details or check_stay_price, though it does not explicitly name sibling alternatives.

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 REQUIREMENT section gives explicit context: update_stay_dates should already be set and the hotel should come from previous search results. This tells the agent when the tool is appropriate, but it does not mention when not to use it or name alternative tools.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the action ('Get detailed information') and does not mention whether it is read-only, what happens if the hotel is not found, or any prerequisites like an active session. This minimal disclosure leaves significant behavioral traits undisclosed.

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. The purpose is front-loaded in the first sentence, and the second sentence adds usage context without any fluff or 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?

The description is adequate for a simple get tool with an output schema. It covers the primary use case ('after search_hotels for more details') and mentions the sequencing. However, it lacks explicit details about how to supply session_id and what constitutes 'detailed information,' but the output schema likely covers the return structure. It is minimally viable with clear gaps.

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

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

Schema description coverage is 0%, so the description must compensate. However, it does not mention or explain the two parameters (session_id, hotel_code_or_name). While the names provide some hint, there is no guidance on how to obtain a session_id or what formats hotel_code_or_name accepts, leaving the agent with inadequate parameter semantics.

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 begins with a specific verb and resource: 'Get detailed information for a hotel.' This clearly identifies the tool's purpose. It also distinguishes itself from sibling tools by stating it is used after search_hotels, which prevents confusion with similar search tools.

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

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

The description explicitly provides when to use the tool: 'Use this after search_hotels when the user asks for more details about a recommended option.' This gives clear context and implies search_hotels as the alternative for initial searching, meeting the criteria for explicit usage guidance.

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

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

With no annotations, the description carries full responsibility for behavioral disclosure. It only states 'compact summary' without elaborating on what the state includes, whether the operation is read-only, or how invalid sessions are handled, leaving significant gaps.

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, front-loaded sentence with no wasted words. It effectively communicates the core purpose in minimal space.

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?

Although an output schema exists to define return values, the description lacks essential context such as usage timing, parameter details, and behavioral expectations. For a simple getter tool, this is minimally adequate but not comprehensive.

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

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

The description does not explain the session_id parameter at all. With 0% schema description coverage, the description fails to add meaning beyond the schema's field name and type, offering little 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 a compact summary of the current session state. 'Get' is a specific verb and 'current session state' is a distinct resource, differentiating it from siblings like list_sessions which lists sessions generally.

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

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

No guidance is provided on when to use this tool versus alternatives. The description does not mention any exclusions, prerequisites, or comparisons with sibling tools, leaving the agent without context for selection.

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

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

With no annotations, the description fully carries the transparency burden. It discloses major behavioral constraints: strict schema, no alias mapping, non-supported fields (city, checkin_date/checkout_date), and a redirect for budget constraints. This adds valuable context beyond the tool name and schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Concise and front-loaded with the primary purpose. The IMPORTANT section uses bullet-like formatting for clarity. Every sentence serves a purpose—no 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 (no parameters, output schema exists), the description is complete: it states the purpose, usage trigger, and key restrictions. It adequately prepares the agent to 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?

Tool has zero parameters, so there is no parameter semantics to clarify. Baseline 4 is appropriate; description does not need to add parameter 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 states a clear verb and resource: 'Return the strict standard schema for user_profile.' It also distinguishes itself from sibling tools by focusing on schema retrieval rather than extraction or updating, and lists what fields are not allowed.

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 says 'Use this tool when the external model is unsure what fields are allowed.' However, it does not provide when-not-to-use guidance or mention specific alternatives beyond implicit differentiation from 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It only restates the tool's purpose ('Health check') without explaining what the check entails, what happens on failure, whether any side effects occur, or what the response contains. This is a minimal disclosure, insufficient for a tool with zero annotation support.

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 sentence that directly states the tool's purpose. Every word contributes value, and there is no redundancy or unnecessary detail.

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 parameterless health check with an output schema available, the description fully suffices. The tool is extremely simple, and the one-sentence description, combined with the schema, provides enough context for an agent to select and invoke it 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?

This tool has zero parameters, so the schema already fully defines the input. The description does not need to add parameter details. The baseline of 4 applies because with no parameters, no additional semantic explanation is required.

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 that this tool performs a health check on the MCP server, which is a specific operation and target. It is immediately distinguishable from all sibling tools, which are domain-specific (search, booking, session management), so there is no ambiguity.

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 usage is implied by the tool's name and description: use it when you need to verify server health. However, there is no explicit guidance about when to choose it over alternatives or any exclusion criteria. Given that all sibling tools are unrelated, the context is still reasonably clear but not formally stated.

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 to rely on, the description discloses key behavioral traits: it appends raw text into user_info (not overwrite) and does not aggressively infer profile fields by default. It also mentions the optional fallback extraction behavior. While it does not cover error handling or side effects of the 'merge' parameter, it provides substantial context beyond the bare schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear sections (IMPORTANT, RECOMMENDED USE, DEFAULT BEHAVIOR, OPTIONAL). Every sentence adds value, and the front-loaded core purpose makes it scannable. The length is appropriate for the tool's complexity.

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 purpose, recommended workflow, default behavior, and an optional parameter. It also references the sibling tool update_user_profile_from_model for the next step, providing valuable context. Minor gaps include lack of detail on the 'merge' parameter and potential side effects, but overall it is quite complete, especially given 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?

The schema has no descriptions for parameters, so the description must compensate. It adds meaning for 'message' (raw user text) and 'use_fallback_extraction' (lightweight fallback extractor). However, 'session_id' and especially 'merge' remain unexplained, leaving a gap in full 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's function with 'Store raw user message into session context' and further specifies 'append raw text into user_info'. It explicitly distinguishes itself from siblings by stating 'This tool is no longer the main profile extraction path' and recommending update_user_profile_from_model for that purpose, making the tool's specific role clear.

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 usage guidance: it recommends when to use the tool ('store raw user text for context'), states what not to do ('do not aggressively infer profile fields'), and names the preferred alternative tool to call afterward ('then call update_user_profile_from_model(...)'). This 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?

With no annotations, the description must carry the burden of behavioral disclosure. It notes the 'in-memory' aspect and implies a read-only list operation, but does not explicitly state that no sessions are altered or that the data is volatile. This leaves some gap for a tool with zero annotation support.

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 deliver the purpose and usage context with no wasted words. Every sentence 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 tool with no parameters and an output schema available, the description covers the essential 'what' and 'when to use'. It does not explain what a 'session summary' contains, but the output schema presumably 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 tool has zero parameters, and the schema is empty. Per the rubric, the baseline for 0 params is 4. The description adds no parameter details, but none are needed.

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 ('List') and the resource ('all in-memory session summaries'), making it distinct from sibling tools like get_session_state or clear_session. It leaves no ambiguity about what the tool does.

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?

'Useful for debugging only' provides a clear context and an implied restriction, telling the agent this is not for general use. However, it does not name explicit alternatives or elaborate on when to prefer other session tools.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals that it doesn't use session state and that user_profile is limited to standard fields, but it does not disclose error behavior, output format, or what 'normalize' entails beyond parsing. This leaves significant behavioral unknowns.

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 short and front-loaded with the main purpose, but the third sentence ('city is not required here') is confusing because city is not in the schema, and it may mislead the agent. It is concise but not cleanly structured.

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

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

Even though an output schema exists, the description is incomplete for a 4-parameter tool with no annotation support. It lacks crucial input requirements and behavioral details, making it difficult for an agent to know how to correctly invoke the tool beyond the obvious parameter names.

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 schema has 0% description coverage, so the description must compensate. It adds that user_profile is optional and accepts only standard profile fields, and that city is not required, but it does not explain the format or relationship of checkin_str, nights, or checkout_str. The main parameters remain underdescribed.

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 a specific verb ('Parse') and resource ('stay dates'), and distinguishes itself from session-dependent siblings with 'without using session state.' This clearly differentiates it from tools like update_stay_dates that operate within a session context.

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 phrase 'without using session state' gives a clear usage context (use this when session state is not needed), but it does not explicitly name alternatives or state when not to use this tool. The additional notes about user_profile and city provide some constraints but not full 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?

No annotations are present, so the description carries the disclosure burden. It reveals the city fallback behavior but does not explicitly state whether the operation is read-only, whether a valid session must exist, or what happens if session.city is absent. The output schema covers return structure, but side effects and preconditions remain under-specified.

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: the first states the core purpose, the second adds a critical fallback rule. It is front-loaded, efficient, and every sentence 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 low parameter complexity and the presence of an output schema, the description covers the main behavior and key city fallback. It does not specify error conditions when no session.city exists, but overall it is sufficiently complete for an agent to use the tool correctly in most scenarios.

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%, so the description must compensate. It adds meaningful semantics for the city parameter by explaining the fallback to session.city when omitted. However, limit and session_id are not described beyond what their titles and defaults imply, leaving only partial compensation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with the specific verb 'Search' and the resource 'activities' scoped to 'a city', which clearly distinguishes it from siblings like search_hotels or search_restaurants_near_hotel. The purpose is immediately 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 a clear usage condition: if city is omitted, fall back to session.city from a prior hotel search. This gives useful contextual guidance, though it does not explicitly mention alternatives or when not to use the 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?

With no annotations, the description carries full responsibility for behavioral disclosure. It simply says 'search' and gives no indication of side effects, read-only nature, return structure, or any operational constraints.

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 in word count but under-specified. It lacks structural elements like context, constraints, or parameter details, making it not appropriately sized for a tool with this level of complexity.

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 severely underspecified. With no annotations, incomplete description, and no usage context, an agent cannot reliably select or invoke this tool. The presence of an output schema does not remedy the lack of behavioral and parameter information.

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 three parameters (limit, session_id, airline_tag) but the description provides zero information about their meaning or usage. Schema description coverage is 0%, and the description does not compensate at all.

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 'Search airline-related content' names a verb and a vague resource, but 'airline-related content' is unclear—it could mean flights, deals, or airline information. It does not meaningfully distinguish this from sibling search tools like search_hotels or search_activities_in_city.

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

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

No guidance is provided on when to use this tool versus alternatives. There is no mention of use cases, exclusions, or prerequisites, leaving the agent without direction for tool selection.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It reveals an important fallback behavior (use session.city) that is not obvious from the schema. However, it does not disclose whether the operation is read-only or any other side effects, leaving room for uncertainty.

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 the primary purpose, and every word earns its place. No fluff; the fallback instruction is a necessary addition.

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 main search intent and the fallback, and an output schema exists so return values are handled. However, it leaves gaps such as the semantics of 'limit' and behavior when session.city is unavailable. For a simple search tool, it is adequate but not 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 description coverage is 0%, so the description must compensate. It only clarifies the 'city' parameter's optionality and fallback, but provides no additional meaning for 'limit' (the default 3 is not explained) or 'session_id' (required but not contextualized). The description helps with one of three parameters.

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 the action ('Search'), the resource ('homestays'), and the scope ('in a city'), clearly distinguishing it from sibling tools like search_hotels and search_activities_in_city. It 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?

The description gives a clear contextual instruction: if city is omitted, use session.city from a prior hotel search. This helps the agent know when the tool can be used and how the city parameter is derived. However, it does not explicitly mention alternatives or exclusions, so it is not a 5.

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

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

With no annotations, the description carries the full burden. It does disclose that the tool depends on session state and profile (via the recommended order), but it does not explicitly state whether the tool is read-only, mutates session state, or has any side effects. It also does not mention failure modes or prerequisites beyond the order. This is moderate transparency for a search-like tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-organized with clear sections: opening purpose, 'USE THIS TOOL FOR', 'IMPORTANT', and 'RECOMMENDED ORDER'. It front-loads the core purpose. However, there is some redundancy, such as repeating the same order details in 'IMPORTANT' and 'RECOMMENDED ORDER', and 'main search intent' is vague. Overall, it is efficient and scannable.

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 an output schema, the tool has 16 parameters, no annotations, and 0% schema description coverage. The description covers only a few key constraints (city placement, date/profile pre-setup) and does not explain the majority of parameters. It does not address how this tool relates to alternatives like search_homestays_in_city beyond the implied hotel focus. The workflow guidance is helpful but insufficient for a tool of this 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?

The schema has 0% description coverage, so the description must compensate. It names price_min/price_max and room/amenity filters, but these are only broad hints. The remaining 13 parameters (e.g., suitable, surroundings, non_refundable, exclude_hotel_codes, required_name_terms, user_specific) are completely unexplained. The description provides little value in clarifying parameter semantics for a 16-parameter tool.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Search and recommend hotels' which clearly states the verb and resource. It further specifies 'city-based hotel search' and 'main search intent', distinguishing it from sibling tools like search_homestays_in_city, search_restaurants_near_hotel, and search_activities_in_city. The resource (hotels) is 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 'USE THIS TOOL FOR' bullet list explicitly states when to use this tool. The 'IMPORTANT' section provides clear exclusions, such as 'city MUST be passed here, not inside user_profile' and 'user_profile is for stable preferences, not for search location'. The 'RECOMMENDED ORDER' gives step-by-step prerequisites, including calling update_stay_dates and update_user_profile_from_model first, which tells the agent when to use this tool relative to others.

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. However, it merely restates the tool's name and purpose, offering no details about side effects, required session state, output format, or how hotel proximity is determined. This is essentially tautological.

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 and front-loaded with no fluff, but it is under-specified for a tool with 5 parameters and no annotations. It is a single sentence that is appropriate in length only if the other tools or schema compensated, which they do not.

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 5 parameters, one required session_id, no annotations, and an output schema (not shown). The description is a single vague sentence that fails to mention how the hotel is identified, whether session_id is essential, or what kind of results are returned. This is far from 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 description coverage is 0%, and the description provides no parameter information. The tool has 5 parameters (hotel_lat, hotel_lon, session_id, hotel_index, hotel_code_or_name) with only required session_id, yet none of this is explained, leaving the agent unable to understand how to specify which hotel.

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 a clear action ('Search') and resource ('restaurants') with a locational context ('near a hotel'). While it distinguishes this from sibling tools like 'search_hotels' or 'search_activities_in_city', it does not specify how the hotel is identified or what 'near' means, preventing a complete differentiation.

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

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

No guidance is provided on when to use this tool versus sibling search tools, nor any exclusions or prerequisites. The description only restates the tool's basic function without hinting at session requirements or hotel identification methods.

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

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

With no annotations, the description carries full responsibility for behavioral disclosure. It explicitly says 'Create or replace a session' (indicating it may overwrite existing state) and clarifies that it initializes conversation state. It also explains that user_profile should only contain stable fields. While it doesn't disclose details like side effects on existing sessions or authorization requirements, the 'replace' wording and workflow guidance provide meaningful behavioral context beyond a simple action label.

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 sections: PURPOSE, DO, DO NOT, CORRECT WORKFLOW, WRONG/RIGHT examples. Each section serves a purpose and the examples illustrate constraints effectively. It is longer than a minimal description, but the structured format and front-loaded purpose sentence make it easy to scan and use.

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 and no annotations, the description covers the core workflow, constraints, and relationship to sibling tools. It explains when to call it, what to pass, and what to avoid. However, it omits any explanation of required session_id, user_id, or metadata, and doesn't mention return values. Since an output schema exists, return values need not be explained, but the missing parameter semantics leave some gaps in completeness.

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

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

Schema coverage is 0%, so the description must compensate. It adds meaning for user_profile and preferred_language, including explicit guidance that city, checkin_date, checkout_date, and search filters must not go into user_profile. However, it fails to explain the required session_id parameter or the purpose of user_id and metadata. This is a notable gap, though the description does provide meaningful semantics for the most complex parameters.

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 'Create or replace a session' and outlines its purpose to initialize conversation state and store stable user profile fields. This distinguishes it from sibling tools like clear_session, get_session_state, and update_user_profile, as it is the session initialization entry point.

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 workflow instructions: 'call this before other hotel-related tools' and lists a correct sequence (start_session -> update_user_profile_from_model -> update_stay_dates -> search_hotels). It also gives DO and DO NOT lists, including exclusions for what should not be placed in user_profile (city, checkin_date, checkout_date, search filters), and demonstrates both wrong and right usage examples.

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

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

No annotations are provided, so the description must disclose side effects. It only says 'Update session stay dates' and gives exclusions, but does not state what happens to existing dates, whether checkout is derived from nights, or any validation or prerequisite behavior. This is insufficient for a mutating tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short, front-loaded, and uses clear headings for use cases and exclusions. Every line contributes useful information with no 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?

With no annotations, the description should cover important behavioral context. It covers purpose and selection well, but omits edge cases like what happens if both checkout and nights are provided, required session validity, or input validation rules. The output schema exists, so return values are covered elsewhere.

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 coverage, the description partially compensates by mapping 'check-in date', 'check-out date', and 'nights-based date calculation' to the relevant parameters. However, it does not explain date formats, optionality beyond schema defaults, or behavior when multiple date-related parameters conflict.

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 'Update session stay dates' with a specific verb and resource. The 'USE THIS TOOL FOR' list and explicit 'DO NOT' exclusions distinguish it from siblings like update_user_profile and start_session.

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 'USE THIS TOOL FOR' and 'DO NOT' sections explicitly tell the agent when to use this tool and when not to, naming alternative targets (user_profile, start_session). This provides strong selection 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?

No annotations are provided, so the description carries the burden of behavioral disclosure. It adds context about standard vs non-standard fields and exclusions, but omits details about the 'merge' parameter's behavior (whether it merges or overwrites) and any side effects or requirements. This is a meaningful gap for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear headings and bullet lists, making it scannable. While slightly verbose, each section contributes relevant information about usage, exclusions, and preferred fields. The format aids comprehension without excessive fluff.

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 profile update tool with an output schema, the description provides adequate guidance on when to use it, what fields to include/exclude, and a list of preferred fields. Missing details about merge semantics and validation behavior prevent a perfect score, but overall it is sufficiently complete for an agent to invoke it 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?

With 0% schema description coverage, the description compensates by listing preferred profile fields and explicitly prohibiting certain fields (city, dates, raw constraints). This adds semantic meaning to the user_profile object beyond its generic schema definition, though the 'merge' parameter is left unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states 'Update session.user_profile' with a specific verb and resource, and further clarifies 'using standard UserProfile fields only', distinguishing it from the sibling 'update_user_profile_from_model'. It also enumerates forbidden fields, making the 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?

Explicit 'USE THIS WHEN' clause indicates the intended scenario (caller already has structured profile fields), and 'DO NOT PUT HERE' lists exclusions that clearly redirect to search_hotels for raw numeric constraints. This precisely guides tool selection 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?

No annotations are provided, so the description carries the full burden. It discloses allowed fields, forbidden fields, and the rule to avoid guessing. However, it does not describe merge/overwrite behavior or what happens when invalid fields are sent, leaving some behavioral ambiguity.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear sections (HARD RULES, GOOD EXAMPLE, BAD EXAMPLE). Every sentence adds value, and the examples are compact yet informative. Nothing is redundant.

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 no annotations, the description fully compensates by explaining the expected input format, constraints, and providing a concrete example. It is complete enough for an agent to invoke the tool correctly without external 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 description coverage is 0%, but the description gives extensive detail for the main 'extracted_user_profile' parameter, including a GOOD EXAMPLE and a BAD EXAMPLE. It clarifies that only standard UserProfile fields are allowed, which is critical given the schema's 'additionalProperties: true'. The other parameters (session_id, merge) are self-explanatory.

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 is the 'Preferred path for profile extraction' and describes the workflow of sending standard UserProfile fields. It distinguishes itself from other tools by focusing on model-driven extraction, but it does not explicitly name alternatives or contrast with 'update_user_profile'.

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

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

Provides explicit when-to-use guidance ('Preferred path'), what to include, and multiple hard rules (e.g., 'do NOT put city here', 'omit uncertain fields'). It also directs numeric budget constraints to 'search_hotels price_min/price_max', clearly indicating an alternative tool.

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