Privatized holiday house for 10 near Rouen, Normandy: info, dog stays, rules, availability, quotes.
Scored across 6 tools
Each tool anchors a distinct question: calendar check, price, property facts, rules, dog policy, and where to book. The one real overlap is between get_dog_information and get_stay_rules, which both discuss dog approval and fees, so an agent may fetch both to answer a single dog question. Still, the descriptions' explicit 'never approves / never confirms' framing keeps intent separable.
Every name follows a verb_noun pattern (get_* for five tools, check_ for the live calendar read), and the single deviation is semantically motivated rather than arbitrary. No casing or style mixing.
Six tools is a tight, well-scoped surface for a single rental property, and each one maps to a distinct visitor question (availability, price, property, rules, dogs, booking channel). Nothing looks redundant or padded.
The discovery-to-booking lifecycle is covered, and the absence of a booking/payment tool is deliberate and clearly documented as external. Minor gaps remain for adjacent needs such as location/directions or reviews, which an agent would have to work around via get_property_information or get_booking_options.
Check a bounded stay against the live authoritative calendar. An unknown source returns source_unavailable; a positive result never holds inventory or approves dogs.
| Name | Required | Description | Default |
|---|---|---|---|
| dogs | No | Number of companion dogs; every dog requires prior host approval | |
| adults | Yes | ||
| check_in | Yes | Local arrival date, YYYY-MM-DD | |
| children | No | ||
| check_out | Yes | Local departure date, YYYY-MM-DD |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the read-only/idempotent/non-destructive profile, and the description adds genuinely non-obvious semantics beyond them: an unknown source yields source_unavailable, and a positive result neither holds inventory nor approves dogs. That prevents an agent from treating a positive check as a reservation or dog clearance. It does not mention rate limits or what a negative result contains.
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, zero waste, with the core action front-loaded and the behavioral caveats compressed into a single clause. Every phrase carries signal.
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 carries the burden of describing returns; it covers only the source_unavailable edge case and the 'no hold' guarantee. What a positive or negative availability result actually looks like, and any capacity/date-constraint rules, remain unstated for a 5-parameter availability tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 60%, with check_in/check_out and dogs already documented in-schema. The description adds the notion that the stay must be 'bounded' (a range, not open-ended) and reinforces that dog approval is a separate step, but it says nothing about adults/children or date-ordering constraints, so it only partially compensates for the coverage gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Check a bounded stay against the live authoritative calendar') and the word 'authoritative' hints at the distinction from get_quote or get_booking_options. It does not explicitly name a sibling, so an agent must infer the split from the phrasing alone.
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 only implied: the 'bounded stay' framing suggests this is a pre-booking availability probe, but the description never says when to call this instead of get_quote or get_booking_options, nor any prerequisite ordering. No exclusions or alternatives are stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Official website, booking page and public contact. Booking and payment are completed on the official site, never inside this AI tool.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, non-destructive, closed-world. The description adds a genuinely useful constraint not implied by annotations: nothing is booked or paid inside this AI tool, all transactions happen on the official site. That is the key behavioral fact an agent needs.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no filler, and the important constraint (booking/payment happen off-tool) is placed second for emphasis after the payload description. Nothing 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?
There is no output schema, so the description must carry the return shape, and it does at a high level (website, booking page, contact). It stops short of saying how the data is structured (single link vs. list of contacts) but is sufficient for a zero-parameter lookup 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?
Zero parameters, so there is nothing to document and no schema gap; baseline 4 applies. The description correctly implies the call is parameterless by presenting it as a fixed pointer to official channels.
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 names the concrete payload — official website, booking page and public contact — which tells an agent what the tool returns. It lacks an explicit verb ('returns the ...') and only loosely differentiates from siblings like check_availability and get_quote, but the resource is 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?
Use is implied by the framing: this is the tool for booking and payment, which are handled off-tool. However, no sibling is named and there is no explicit 'use this when the user wants to book, not when they want prices/availability' routing statement.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Public QUALIDOG label and dog-stay FAQ in French, English, German or Dutch, with canonical sources. Covers prior host approval, fees, enclosed garden, preparing your stay and local outings. Checked against current property rules and fees; never approves a dog or confirms a booking.
| Name | Required | Description | Default |
|---|---|---|---|
| language | No | fr |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish that this is a read-only, idempotent, non-destructive lookup. The description adds meaningful behavioral context: it is public, uses canonical sources, is checked against current property rules and fees, and does not itself approve dogs or confirm bookings.
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 and front-loaded: it first states what content is provided, then summarizes coverage, then clarifies the non-booking boundary. Every sentence contributes useful information without repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple read-only information lookup with one optional parameter and no output schema, the description is complete enough to guide use. It covers scope, language options, sources, freshness, and the key limitation that it does not perform approvals or booking actions.
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 is one optional language parameter, but schema description coverage is 0%. The description lists the supported languages in natural language, which helps interpret the enum, but it does not state the parameter name, default behavior, or what happens if the parameter is omitted.
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 identifies a specific resource: public QUALIDOG label and dog-stay FAQ content, including the topics it covers. It is clearly dog-stay-specific, but it does not explicitly distinguish itself from sibling tools such as get_stay_rules or get_property_information.
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 title and description give a clear use context: planning a stay with a dog and answering dog-specific stay questions. It also states a useful boundary — it never approves a dog or confirms a booking — though it does not explicitly name which sibling tool to use for booking or approval.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Public verified description, capacity and facilities of the fully privatized property near Rouen. French source text may be translated by the assistant.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, idempotent, closed-world, non-destructive behavior, so the description's job is to add what annotations cannot. It does: the content is 'public' and 'verified' (authoritative rather than user-generated) and the source text is French and may need translation — a genuinely actionable operational note. It stops short of describing structure or whether any proprietary/pricing data is excluded.
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 waste, and the payload description is front-loaded. The opening reads as a sentence fragment ('Public verified description, capacity and facilities'), which is slightly awkward but costs no comprehension.
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 output schema, the description carries the burden of saying what comes back, and it enumerates the three content areas plus the language caveat. Missing only scope boundaries such as whether location/contact or pricing details are included, which an agent might otherwise assume.
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 and the schema is fully closed (additionalProperties: false), so there is nothing for the description to clarify. Baseline for a no-param tool is 4; the description correctly implies no arguments 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 names the specific content returned — public verified description, capacity, and facilities of the privatized property near Rouen — which lets an agent distinguish it from siblings like get_quote or check_availability. It is a noun-phrase inventory rather than a verb+resource statement, but the resource and payload are 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?
Usage is implied: this is the general discovery/informational call, and the siblings cover availability, booking options, quotes, stay rules, and dog policy. However, the description never states when to call this first, whether it should precede check_availability or get_quote, or any exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return a verified total in EUR minor units only when live availability, rates, fees and taxes are complete. A priced dog stay still needs host approval. Otherwise report incomplete or source_unavailable, never an estimated total.
| Name | Required | Description | Default |
|---|---|---|---|
| dogs | No | Number of companion dogs; every dog requires prior host approval | |
| adults | Yes | ||
| check_in | Yes | Local arrival date, YYYY-MM-DD | |
| children | No | ||
| check_out | Yes | Local departure date, YYYY-MM-DD |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare this as a safe, read-only, idempotent operation, but the description adds critical business behavior: no estimated totals, explicit fallback statuses (incomplete, source_unavailable), and the host-approval constraint for dog stays. These details materially affect what the agent can report and when.
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 short sentences, front-loaded with the primary behavior and followed by the key exception and fallback rule. No filler 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?
With no output schema and a five-parameter quote tool, the description explains the critical return conditions and failure states. It leaves some details of the successful response shape implicit, but the behavioral essentials for correct invocation are covered.
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 60%: check_in, check_out, and dogs are documented in the schema, while adults and children are not. The description only mentions the dog approval rule, which duplicates the schema's own dogs description, and adds no meaning for adults or children.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource: returns a verified total in EUR minor units, with explicit conditions about completeness. It implicitly differentiates from availability-oriented siblings like check_availability, though it does not name any sibling directly.
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?
Gives clear conditional guidance: return a total only when live availability, rates, fees, and taxes are complete; otherwise report incomplete or source_unavailable. It also notes that a priced dog stay still requires host approval, which tells the agent when a total is not final.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Public check-in, check-out, group, dog, cleaning and event rules. Every dog needs prior host approval. Amounts are EUR minor units and do not replace a live total quote.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish read-only, idempotent, closed-world behavior. The description adds useful context beyond annotations: rules are public, dog stays require prior host approval, amounts are in EUR minor units, and fee amounts are not a live total quote.
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, both front-loaded and functional: the first defines the rule categories, and the second adds critical caveats about dog approval and EUR minor-unit amounts. There is no wasted text.
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, read-only tool with rich annotations and no output schema, the description is nearly complete: it lists the rule categories and key caveats. It could be slightly stronger by stating the return shape or explicitly routing quote-related questions to get_quote.
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, so there are no parameter semantics for the description to compensate for. Baseline 4 applies for a no-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 identifies the resource as public stay rules covering check-in, check-out, group, dog, cleaning, and event rules. It does not explicitly name a verb or distinguish this tool from siblings like get_dog_information or get_quote, but the resource scope is understandable.
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 explicit when-to-use guidance or named alternative. The caveat that amounts 'do not replace a live total quote' implicitly points agents to get_quote for pricing, but the description does not state when to choose this tool over get_dog_information or get_booking_options.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
check_availabilityget_booking_optionsget_dog_informationget_property_informationget_quoteget_stay_rulesCarp fishing lakes in France: search venues, check availability, get week prices, book.
Live availability and commission-free booking links for resort La Truite d'Argent, Belgian Ardennes
Private driver in Beaune, Burgundy: places, events, prices, availability, quotes, bookings.
FR/EN tools for French rental, frontalier & home-employment (CCN 3239) — sourced, dated answers.
Add one secure layer between your agents and this server.
