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 transparently states the key outcome—nothing is added, only a report. This is sufficient to prevent an agent from expecting a successful state change, though it does not detail response format or potential errors.

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 with no filler. The key fact (unsupported) is front-loaded, and the behavioral outcome follows immediately. 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 single-parameter no-op tool with no output schema, the description captures the essential behavior. It tells the agent the tool is a stub and its expected result. It could mention what the 'report' looks like, but that is a minor gap given the simplicity.

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 context by indicating the extras parameter is not honored—nothing will be added regardless of its value. However, it does not elaborate on input validation or the meaning of each enum value, which the schema already enumerates.

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 what the tool does: it reports that nothing was added because extras are not supported. This is not a tautology and gives a concrete behavior. It distinguishes itself from siblings by explicitly noting the unsupported nature.

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 it should not be relied upon for adding extras ('Extras are not supported by this adapter'), which is a form of usage guidance. However, it does not explicitly name alternatives or state conditions for when this tool should be called, leaving some ambiguity.

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. It discloses that this is a preview operation, requires explicit user approval, and needs a confirmationToken to actually confirm. This is strong for a destructive operation, though it could further mention irreversibility or authorization requirements.

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 with no filler. The core action 'Preview a cancellation' is front-loaded, and the confirmation flow is stated efficiently.

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 captures the essential two-phase flow but leaves some gaps: it does not explicitly state that confirmationToken comes from the preview response, what the preview returns, or how to handle errors. For a low-complexity tool without an output schema, this 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 add meaning. It explains that confirmationNumber is reused across both calls and that confirmationToken is the artifact needed for the confirmed cancellation, giving workflow-level semantics beyond the raw schema names.

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 previews a cancellation and then confirms it by repeating the same confirmationNumber with a confirmationToken. This differentiates it from sibling tools like modify_reservation by naming cancellation as the specific 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 provides a clear two-step workflow: first preview the cancellation, then after explicit user approval call again with the confirmationToken. It does not explicitly mention alternatives like modify_reservation for non-cancellation changes, but the intended usage is well 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It only says 'Request mobile check-in' without revealing side effects, authentication requirements, or whether the operation mutates reservation state. The action word 'request' hints at a non-destructive operation but does not confirm it.

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, concise sentence with no wasted words. It is appropriately short, though it sacrifices critical detail for brevity. Structurally, it is front-loaded with the core action.

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

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

Given no annotations, no output schema, and a sparse description, the tool is severely incomplete. It fails to explain return values, prerequisites, side effects, or parameter semantics, leaving an agent with insufficient information to call 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?

Schema description coverage is 0%, so the description must compensate by explaining the parameters. It does not mention confirmationNumber, roomPreferences, or estimatedArrivalTime at all, providing zero guidance on their meaning or usage beyond what the schema itself gives (names/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 states a specific action ('Request') on a specific resource ('mobile check-in') with a condition ('for an existing reservation'). It clearly distinguishes from siblings like modify_reservation or cancel_reservation, so an agent can tell what this tool does without opening the schema.

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 'for an existing reservation' implies the user must already have a reservation, but it does not explicitly mention when not to use this tool or name alternatives. There is no guidance on how it differs from get_reservation or status, leaving the agent to infer 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?

With no annotations, the description carries the full burden. It discloses the two-step nature, the requirement for explicit user approval, the effect of changed price/terms, and the eligibility confirmation conditions. It also warns against retrying unknown outcomes, which is a key behavioral constraint. It does not mention side effects like booking finalization, but the token flow implies that.

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 compact yet information-dense, front-loading the purpose and then logically sequencing the workflow, conditions, and a warning. Every sentence adds value, and there is no 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?

The tool is complex with 16 parameters and no output schema. The description explains the two-step process and key flags, but it omits details on which parameters are needed in each call, error handling beyond unknown outcomes, and what the preview response contains. An agent might not know exactly what to supply for the first call without additional inference.

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

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

Schema coverage is 0%, so the description must explain parameters. It explains confirmationToken, governmentEligibilityConfirmed, and specialRateEligibilityConfirmed, which are critical. However, it does not clarify the roles of the other 13 parameters (email, phone, dates, guest counts, etc.) beyond the general phrase 'guest details.' It does not indicate which are required for the first call versus the token-only call, leaving some ambiguity.

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 prepares a checkout preview for a given offerId, which is a specific verb-resource pair. It distinguishes itself from siblings like select_room or add_extras by focusing on the checkout step, though it does not explicitly name 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?

It provides explicit workflow guidance: call once to get a token, then call again with that token after user approval. It also specifies conditions for eligibility flags and warns against retrying unknown outcomes. However, it does not state when to prefer this over other booking tools or what precedes it in the flow.

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 that the tool 'Reads' data, implying a non-destructive operation, but it does not disclose authentication requirements, whether it requires a prior login, the response shape, or any error conditions. For a tool that likely depends on session state, this is a significant gap.

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, tight sentence with no filler or redundancy. It front-loads the action and the resource, making the purpose instantly clear. Every word earns its place, and the brevity is appropriate given the tool's simplicity.

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

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

For a tool with no parameters and no output schema, the description is minimal but lacks critical context. It does not mention that the user may need an active session or that the data might be stale or require authentication. The presence of sibling tools like 'login', 'logout', and 'status' suggests integration with session flow, which is not addressed. An agent cannot fully determine when or how to invoke this tool correctly without additional assumptions.

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 input schema is an empty object, so the description has no parameter information to add. Per the baseline rule for 0-parameter tools, a score of 4 is appropriate. The description does not contradict the schema and provides the minimal context needed for a parameterless read.

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 a verb ('Read') and a specific resource ('Marriott Bonvoy points and tier status'). It is unambiguous and provides enough detail to distinguish from the generic sibling 'status' by naming the loyalty program and what is read. However, it does not explicitly name alternative tools or contrast its scope, so it falls just short of a 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?

There is no guidance on when to use this tool versus alternatives. The description does not mention prerequisites (e.g., active session) or scenarios where this tool is preferred over 'status' or other read tools. An agent would have to infer the usage context entirely from the name and 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 full responsibility for behavioral disclosure. It only states 'Get property details' which implies a read operation, but does not mention any side effects, authentication requirements, rate limits, or what the response contains. This is insufficient for a tool with zero annotation coverage.

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 that conveys the essential action and input without any filler. It is appropriately concise and easy to parse.

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 one-parameter tool with no output schema, the description covers the input type but omits details about the response structure, potential errors, or any behavioral constraints. Given the lack of annotations and output schema, this is a moderate gap – the agent knows what to call but not what to expect back.

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 schema description coverage at 0%, the description is the sole source of parameter meaning. It adds clarity by specifying that the parameter is a 'Marriott property code or URL', which goes beyond the schema's generic pattern and URI format. This gives the agent a clear understanding of what to pass.

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 (get) and resource (property details), and specifies the input type (Marriott property code or URL). It doesn't explicitly distinguish from sibling tools like search_hotels, but the purpose is unambiguous and self-contained.

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 retrieving details of a specific known property, but provides no explicit guidance on when to use it over alternatives like search_hotels or get_room_options. There is no mention of when not to use it or what scenarios favor this tool, so guidance is only 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool reads reservations, which implies non-destructive behavior, but does not mention return format (list vs. single), pagination, error handling, or any side effects. The description is minimal and does not adequately disclose behavior beyond the action itself.

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, concise sentence that front-loads the primary purpose and quickly mentions the optional filter. There is no unnecessary wording, and it is efficient for an agent to parse.

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 one optional parameter and no output schema. The description covers the core action and parameter role, but it omits the exact return behavior (e.g., list vs. single reservation) and does not guide when to use this tool versus siblings. While adequate for a basic read, it leaves some gaps that an agent might need filled.

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 explains that confirmationNumber is used to filter results, which adds semantic meaning beyond the parameter name. However, it does not clarify the pattern constraints or the effect of omitting the parameter (e.g., returns all upcoming). The description provides basic role but lacks detail.

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 a specific action (read) and resource (upcoming Marriott reservations), and distinguishes itself from siblings like get_stay_history by specifying 'upcoming'. This differentiates it without 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 description implies usage context (upcoming reservations) and mentions optional filtering, but does not explicitly state when to prefer this over get_stay_history or other tools, nor does it provide exclusions or alternatives. The guidance is implicit rather than explicit.

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 discloses that no rate is auto-selected or ranked, that missing terms remain unknown, that usePoints supports only regular award inventory, and that government scope defaults to federal-only. It also instructs to review options with the user before choosing an offerId. This is comprehensive for a read-only 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 compact yet information-dense, with the core function stated first and key caveats following. Every sentence adds value, and it avoids redundancy. It is appropriately sized 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?

Given 11 parameters, no output schema, and no annotations, the description covers the essential behaviors, defaults, limitations, and workflow. It could be more detailed on the structure of rateResults or how to interpret cancellation terms, but it gives enough to call the tool correctly. The missing details are not critical for 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 only 36%, so the description must compensate. It adds meaning to specialRates (categories to search separately), usePoints (regular award inventory only), governmentScope (defaults to federal-only), and corporateCode (implied for corporate_promo). It does not explain rooms, adults, children, dates, or hotelId, but those are self-explanatory and covered by schema patterns. Overall, it adds value 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 the tool returns all matching room/rate offers grouped in rateResults for each selected specialRates category, including cancellation policy, deadline, deposit terms, and eligibility. It is specific about the resource (room/rate offers) and the action (returning them), and it distinguishes itself from sibling tools like select_room by explicitly noting that no rate is automatically selected or ranked.

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 on how to use the tool, including that defaults come from MCP environment config, government scope defaults to federal-only, and that review with the user before choosing an offerId is required. It does not explicitly name alternatives (e.g., select_room) or state when not to use it, but the guidance is strong enough to orient an agent.

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. 'Read' implies a safe read operation, but no other behavior is disclosed—no mention of pagination, ordering, what a 'stay' consists of, or whether any side effects occur. The description adds minimal transparency beyond the verb.

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 brief, which could be seen as concise, but it is under-specified rather than efficiently sized. It is front-loaded in the sense that the only information is at the start, but there is no structure or additional detail to justify its brevity.

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 single optional parameter, lack of output schema, and no annotations, the description is wholly inadequate. It does not explain what past stays are, what data is returned, or any ordering or filtering behavior. An agent cannot reliably call this tool based on the description alone.

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 coverage is 0% and the description does not mention the 'limit' parameter at all. The description adds no meaning to the parameter, so the agent has no idea how to set or interpret it.

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 ('Read') and resource ('past stays'), but 'stays' is ambiguous and there is no differentiation from the sibling get_reservation, which likely also deals with stay-related data. The purpose is somewhat clear but not precise enough for an agent to distinguish it.

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 like get_reservation. The description gives no context, prerequisites, or exclusions, leaving the agent to infer usage entirely.

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 disclose behavior. It reveals that it opens a server browser (interactive), optionally uses environment credentials, and finishes with status. Yet it doesn't explain what 'status' means, whether it blocks, or how it affects an existing session – significant gaps for a state-changing operation.

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, a single sentence with three clauses: action, optional credential use, and completion with status. It front-loads the primary purpose. No wasted words, though the phrase 'Finish with status' is slightly ambiguous.

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 login tool with no params and no output schema, the description covers the basics but leaves out critical context: what happens if already logged in, whether it requires a specific environment setup, and what the status output actually contains. Given the interactive nature and potential side effects, this is incomplete.

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 zero parameters, so the schema coverage is trivially 100% and the baseline is 4. The description adds context about environmental credentials, which is not a parameter but relevant operational detail. No further parameter explanation is 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 states a clear action: 'Open the server browser for manual Marriott login' – a specific verb and resource. It also mentions optional credential usage and finishing with status, which adds context. It is distinct from sibling tools like logout and recover_session, though it doesn't explicitly name them.

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?

Usage is implied: it's for logging in manually. However, there is no explicit guidance on when to prefer this over alternatives like recover_session, or what to do if already logged in. The mention of 'manual' suggests a fallback but doesn't spell out conditions.

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. It discloses that it clears auth, pending confirmations, and offers; disconnects Chrome profile but retains sign-in; and retains the booking-attempt journal. This is thorough transparency about side effects and what is preserved.

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 action. It wastes no words and efficiently communicates the core behavior and the key nuance about Chrome sign-in.

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 no-parameter, no-output tool, the description is complete. It covers what is cleared, what is retained, and the Chrome profile behavior, leaving no ambiguity about the tool's effect.

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, so the baseline is 4. The description adds no parameter semantics because none exist, which 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 states a specific verb 'Clear' with clear objects: MCP authentication, pending confirmations, selected offers. It also distinguishes itself from Chrome sign-out, clarifying its exact scope, which differentiates it from sibling tools like login, recover_session, and 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?

It provides guidance on when to use this tool by clarifying that it clears MCP auth but not Chrome sign-in, explicitly directing users to 'sign out in Chrome separately.' This implies the tool is for MCP-level logout, not browser logout. It doesn't mention explicit alternatives but gives clear contextual instructions.

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 discloses that this is a preview step and that confirmation is required, but it does not explicitly state whether the preview itself modifies the reservation or what side effects occur. It also lacks details on error handling or permission requirements.

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 core purpose and followed by the confirmation workflow. There is no redundant or filler content; 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?

The tool has 6 parameters, no output schema, and no annotations. The description explains the workflow but does not cover parameter semantics, expected output of the preview, or error conditions. An agent would struggle to construct valid calls or interpret results without additional 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%, so the description must explain the parameters. It only mentions confirmationToken and the concept of repeating identical parameters, but does not describe the meaning or usage of newCheckIn, newCheckOut, newRoomType, or specialRequests. This is a significant gap for an agent to call the tool correctly.

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 ('Preview') and a clear resource ('reservation changes'), distinguishing it from sibling tools like cancel_reservation or get_reservation. It also conveys the two-phase nature of the operation without 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 description explains the workflow: preview first, then confirm with a token, and that changed parameters require a new preview. It provides clear context on when to call the tool and the confirmation step, though it does not explicitly list alternative tools 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, the description must disclose behavior. It mentions 'Requires headed mode, which is the default', which is a useful behavioral requirement. However, it does not disclose what happens if the session is missing, whether the operation is safe or has side effects, or what the outcome is beyond 'complete a challenge or login'. It adds some context but leaves room for more 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 with no wasted words. The primary purpose is front-loaded, and the critical requirement (headed mode) is stated second. It is concise and 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?

For a zero-parameter tool with no output schema, the description covers the essential purpose and a key requirement. It could be more complete by explaining what a 'challenge' entails or what happens if no session exists, but for a simple recovery action it is largely 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?

The tool has zero parameters, so the schema imposes no burden. The description correctly omits parameter details, and the baseline for parameter semantics is 4 when there are no parameters to document.

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: bringing the same server browser forward to complete a challenge or login. It specifies the resource ('server browser') and the purpose, and it is distinct from sibling tools like 'login' which would initiate a new session. No ambiguity or tautology.

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 when to use it (when a challenge or login is needed) but does not explicitly compare to alternatives or state when not to use it. For example, it doesn't say 'use login instead for new sessions'. The guidance is present but not explicit.

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 behavioral burden. It discloses the need for user approval before confirmation and warns against retrying unknown outcomes. However, it does not describe the mutation's side effects, such as points deduction or reservation creation details, leaving 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 two sentences, front-loading the core purpose and then critical usage rules. It is concise and well-structured, with no fluff. However, the brevity sacrifices completeness, which is penalized elsewhere.

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 16 parameters, no schema descriptions, no output schema, and no annotations, the description is severely incomplete. It does not explain how preview and booking differ, what parameters are required for each scenario, or what the response contains. This is inadequate for an agent to call 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?

The schema has 0% description coverage, and the description provides no parameter explanations beyond mentioning confirmationToken. With 16 parameters, none of which are self-explanatory from names alone (e.g., governmentEligibilityConfirmed, specialRateEligibilityConfirmed), this is a critical gap. The description fails to compensate for the missing 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 tool's function: preview and book an exact award offer from a usePoints search. It distinguishes itself from siblings like search_hotels and get_room_options by specifying the redemption context. The verb 'redeem' is implicit in the name but the description clarifies the specific 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?

It provides explicit conditions: only pass confirmationToken after explicit user approval, and never retry an unknown submission outcome. It implies the tool should be used after a usePoints search, giving context. However, it does not name alternative tools or explicitly state when not to use it, leaving some ambiguity.

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 full behavioral burden, and it does well. It discloses that results are grouped by category, includes cancellation/deposit terms, that no winner is auto-selected (non-committal), that government scope defaults to federal-only, and that adults/children are per room. It does not cover pagination or result limits, but those are partially encoded in parameters. Overall, it adds substantial behavioral context beyond the 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 a single dense paragraph with no wasted words. Each sentence adds value: the main purpose, the grouping and terms, the government default, the note about unknown categories, the no-winner caveat, and the per-room clarification. It is front-loaded with the core function and keeps clarifications brief. Not overly long for the complexity of the tool.

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?

There is no output schema, so the description must describe return values, and it does: 'return all matching offers, grouped by category, with cancellation/deposit terms and eligibility.' It also covers key behavioral nuances like the default scope and the no-selection policy. It could add details on pagination (maxPages/maxResults) or error handling, but given the 12 parameters and the absence of an output schema, it is largely 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 only 33% (4 of 12 parameters have descriptions). The description compensates by explaining key parameters: specialRates is 'searched separately' and returns all offers; governmentScope has a default and filtering logic; rateType is deprecated; adults/children are per room. This adds meaning that the schema lacks, especially for adults/children semantics and the specialRates search behavior.

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: 'Search each selected specialRates category ... and return all matching offers, grouped by category, with cancellation/deposit terms and eligibility.' It names the resource (hotels, implied by tool name and destination parameter) and provides a specific verb. It also differentiates from siblings by explicitly stating 'No winner is selected' and referencing select_room/checkout, which clarifies its role in the workflow.

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 concrete usage context: 'present the options to the user before select_room or checkout' tells when to use this tool versus the selection/checkout steps. It also clarifies defaults (government scope federal-only) and edge cases ('Unknown categories are not sold out'). However, it does not explicitly mention alternatives or when not to use it beyond the workflow sequence, which is slightly less explicit than ideal.

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 behavioral disclosure burden. It discloses that the tool does not submit a reservation and that legacy room codes require an unambiguous ratePlanCode. However, it does not mention side effects, state changes, idempotency, or authentication requirements, leaving gaps in the behavioral 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 extremely concise, consisting of two sentences. The primary purpose is front-loaded in the first sentence, and the second adds a specific condition and a crucial clarification. Every word adds value 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?

For a tool with 4 parameters, no output schema, and no annotations, the description is incomplete. It does not explain the role of hotelId, the response format, or the prerequisites for calling the tool (e.g., that an offerId must come from prior search results). While it gives key usage hints, an agent would still be uncertain about required inputs and expected output.

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 explain all parameters. It clarifies offerId as the selection key and gives context to roomCode/ratePlanCode for legacy codes, but hotelId is not mentioned at all. This leaves a required-looking parameter unexplained, making the description insufficient for a 4-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 clearly states the tool selects an exact offerId from search results, which is a specific verb and resource. It also explicitly notes that it does not submit a reservation, distinguishing it from final checkout steps. This effectively differentiates it from siblings like checkout or add_extras.

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 after search results are obtained (from search results) and mentions a legacy room code condition, but it does not explicitly name alternatives or state when not to use it. The clarification that it does not submit a reservation hints at its role, but explicit routing to siblings is absent.

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 adds useful context about cookie persistence across session types, which explains potential differences in authentication state. However, it does not specify what the tool returns (e.g., a boolean, a message), whether it has side effects beyond verification, or what happens if the user is not authenticated. It gives some behavioral insight but not complete 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 exceptionally concise: two sentences, with the primary purpose front-loaded in the first sentence and supplementary context in the second. There is no redundant language or filler. Every word contributes to understanding the tool's function and behavior.

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 simplicity of the tool (no parameters, no output schema), the description is mostly adequate but leaves a gap: it does not describe the return value or format. For a status verification tool, an agent would benefit from knowing whether the response is a simple boolean, an object with details, or an error message. The description implies verification but omits this detail, making it incomplete for fully autonomous 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?

The tool has zero parameters, and the schema is trivially 100% covered. Per the rubric, a baseline of 4 is appropriate when there are no parameters to explain. The description does not need to add parameter semantics, and it does not attempt to.

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 ('Verify') and resource ('authentication'), clearly distinguishing this tool from siblings like login, logout, and get_bonvoy_status. It immediately conveys that the tool checks authentication state, and the added cookie context clarifies the scope of what is being verified.

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 a clear use case—checking whether a user is authenticated—and the context of session/cookie handling gives relevant background. However, it does not explicitly state when to use this tool versus alternatives like login or logout, nor does it mention any exclusions or prerequisites. The intent is clear but not fully explicit.

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