Samuelz Chauffeur Booking

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds value by clarifying that this is a read of published terms and explicitly states it does not confirm a booking, which is a useful behavioral boundary beyond the annotations.

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

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

Three sentences, each earning its place: the first lists what is read, the second adds a caveat about service-specific terms, and the third clarifies a non-action. 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 has a simple schema with one optional parameter and an output schema, so the description doesn't need to explain return values. It covers the main behavioral boundary (no booking confirmation) and the scope of terms. It could mention that locale is the only parameter, but the schema already does 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?

Schema description coverage is 0%, but there is only one parameter (locale) with an enum and a default. The description does not mention locale at all, so it doesn't add meaning beyond the schema. However, the schema itself is fully self-explanatory for this single parameter, so the baseline 3 is appropriate.

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

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

The description clearly states the tool reads current booking preparation terms, account requirements, guest booking, and minimum lead time. It also explicitly says it does not confirm a booking, which distinguishes it from booking-related siblings like prepare_offer.

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 when to use this tool: to read current terms before confirmation. It also notes that service-specific cancellation and waiting terms must be checked on the current offer, implying this tool is not for those. However, it doesn't explicitly name alternative tools for those cases.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds domain-specific transparency by stating that no quote, booking, payment, message, or provider request is created, which gives assurance beyond the generic annotation hints.

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 sentences with no filler. The core operation is front-loaded, and the side-effect guarantee is provided in a compact second sentence. Every word earns its place.

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

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

For a simple two-parameter read operation, the description covers the purpose, required identifiers, and side-effect profile. An output schema exists, so return-value documentation is not the description's burden. It is slightly incomplete only in not explaining how to obtain a resumeToken or how this relates to prepare_offer.

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 needed to explain what submissionId and resumeToken mean, where they come from, and how they relate to a prepared offer. It only repeats the parameter names in the operation statement, adding almost no semantic value beyond what the parameter names and schema formats already imply.

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

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

The description uses a specific verb and resource: 'Read one prepared offer' by its two identifying tokens. It clearly separates this read operation from quote, booking, payment, message, and provider request creation, which distinguishes it from siblings like quote_ride and prepare_offer.

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 clear context that this is a read-only lookup of a prepared offer, and the explicit statement that no quote or booking is created indirectly signals when not to use it. However, it does not name alternatives or give explicit when-to-use versus when-not-to-use guidance beyond that side-effect disclaimer.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds useful context beyond those annotations by stating the data is 'public' and by naming the returned capability categories, which reinforces that no private or customer-specific data is involved.

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 one short, front-loaded sentence with no filler or repetition. It immediately communicates the verb, resource, and scope without requiring the agent to parse extra prose.

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

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

For a simple read-only tool with a single optional parameter, a rich output schema, and safety annotations, the description is largely complete. Minor gaps are the vagueness of 'required ride facts' and the absence of any guidance on how this differs from related offer and quote tools.

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 mention the locale parameter, but the single optional parameter is already self-explanatory via its name, enum of de/en, and default of de. The schema, rather than the description, carries the parameter semantics; the low descriptive coverage is not a meaningful gap for this trivial parameter.

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

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

The description uses a specific read verb and a concrete resource: 'Read this provider's public service, required ride facts and booking link.' This makes the tool's role clear, though it does not explicitly contrast it with sibling tools like quote_ride or get_offer_status.

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

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

The description implies that this tool is for retrieving provider service options and booking facts, but it gives no explicit when-to-use or when-not-to-use guidance. With siblings like prepare_offer and quote_ride in the same domain, an agent would benefit from clearer routing cues.

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

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

The description adds meaningful behavioral context beyond the annotations: it clarifies that this creates an unpaid reservation, does not charge or confirm the booking, and requires real customer data. It also implies a checkoutUrl in the response. The annotations already declare readOnlyHint=false, idempotentHint=true, and destructiveHint=false, so the description reinforces these without contradicting them. It does not mention idempotency behavior explicitly, but that is covered by the annotation.

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 filler. It front-loads the primary purpose and then lists prerequisites and side-effect clarifications. Every sentence adds value, though some technical jargon (submissionId, resumeToken, opaque capability) could be more accessible. It is appropriately concise 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?

For a tool with 6 parameters, nested objects, and an output schema, the description is incomplete. It fails to explain the ride object's purpose or required fields, the meaning of locale, or how the output checkoutUrl is returned. It does mention that the customer confirms on checkoutUrl, but does not clarify that this is part of the response. The 'Essential one-way transfer' limitation is also unaddressed in the schema, leaving agents uncertain about tripType. Given the lack of schema descriptions, the description leaves too much to 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 description coverage is 0%, so the description is the sole source of parameter meaning. It mentions submissionId, resumeToken, contact, and distributionPartnerCapability (as 'opaque capability'), but it does not explain the 'ride' object fields, 'locale', or the constraints of any parameter. The schema itself has no descriptions, so an agent would be left guessing about required subfields and formats beyond the JSON structure.

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

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

The description clearly states the verb ('Prepare'), the resource (a binding offer), and scope ('exactly one unpaid reservation and binding offer for an Essential one-way transfer'). It also explicitly notes that it does not charge or confirm, which distinguishes it from a booking action. However, the phrase 'Essential one-way transfer' conflicts with the schema's tripType enum that allows both 'one_way' and 'return', creating ambiguity about whether this tool supports round trips.

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 lists prerequisites ('Requires real customer contact data and a client-generated submissionId and resumeToken') and a conditional ('Approved distribution partners may add their opaque capability'). It does not explicitly name sibling tools like quote_ride or get_offer_status, nor does it state when to prefer this tool over alternatives. The context implies it is for finalizing a binding offer rather than getting a quote, but that is not spelled out.

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

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

Annotations already provide readOnlyHint=true and destructiveHint=false, so the description only needs to add context. It adds that there is no availability guarantee, no charge, booking, message, or reservation, and warns against sending customer contact details. This goes beyond the structured annotations and gives the agent important behavioral expectations.

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 three sentences with no filler. The first sentence states the purpose, the second defines exclusions, and the third gives a clear parameter constraint. It is front-loaded 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 output schema exists and annotations are strong, the description covers the non-obvious constraints needed to call correctly: local time, address format, non-binding nature, and privacy rule. It does not elaborate on locale or specialRequests, but the schema and output schema cover those, so the description is reasonably complete for this read-only quote tool.

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

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

Schema description coverage is 0%, so the description must add parameter meaning. It does clarify that time is local service time and that addresses should include city or postcode, and 'complete ride facts' implies all required ride fields. But it leaves locale, specialRequests, returnDate/returnTime, tripType, and passengers largely to schema inference, so compensation is only partial.

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 and output: 'Get a current price preview for complete ride facts.' It also differentiates itself from siblings like prepare_offer by explicitly excluding booking, charge, message, and reservation, making the tool's non-binding quote role unmistakable.

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 gives solid context for when to use the tool: for a current, non-binding price preview, and explicitly says what it does not do (no availability guarantee, booking, charge, message, or reservation). It also instructs not to include customer contact details. However, it does not name sibling tools or explicitly route to prepare_offer when booking is needed, so it lacks a full when-not/alternative mapping.

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