2-bedroom Milan apartment (max 4, near Fiera/EICMA): open dates + direct GuestHost booking links.
Scored across 2 tools
get_booking_link and search_stays have mostly distinct purposes: one returns a static booking link, the other searches availability and returns booking links. However, since search_stays also returns booking links, there is some overlap that could cause mild confusion.
Both tool names follow a clear verb_noun pattern in snake_case (get_booking_link, search_stays). The conventions are consistent and predictable.
Two tools is thin for a booking-related server, even if the scope is narrow. It feels borderline rather than well-scoped.
The domain suggests booking and availability workflows, but there is no tool to actually make or manage a booking, check pricing, or get detailed apartment information. Significant gaps exist for an agent trying to complete a booking task.
Direct booking link (IT/EN) for Oronzo Apartment Washington, Milan.
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation already establishes that this is a safe read operation. The description adds that it returns a direct booking link for a specific apartment and supports IT/EN, but it does not describe the return format, authentication needs, or rate limits. With annotations covering safety, this level of added context is adequate but not rich.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence with zero waste, front-loading the resource and key qualifiers (languages, apartment). It is appropriately sized for 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 simple read-only link getter, the description covers the core purpose and language options. However, with no output schema, it should ideally mention that the return value is a URL, and it lacks any usage context relative to the sibling tool. It is adequate but has clear gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the sole parameter is an enum (it/en). The description repeats the allowed values as '(IT/EN)', which maps directly to the schema's enum and adds some clarity about language, but it does not explain the effect of omitting the parameter or whether a default language exists. Baseline 3 for minimal compensation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific resource — a direct booking link for Oronzo Apartment Washington, Milan — and notes language options (IT/EN). The verb is implied by the tool name rather than stated, and it does not differentiate from the sibling search_stays, but the purpose is clear enough.
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 given on when to use this tool versus alternatives, nor any prerequisites or context. The sibling search_stays is not mentioned, so the agent must infer the appropriate usage scenario.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Direct-bookable apartment in Milan (Oronzo, Via Washington 52). Returns open date windows and GuestHost booking links.
| Name | Required | Description | Default |
|---|---|---|---|
| guests | No | ||
| arrival | No | ||
| departure | No | ||
| destination | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint=true, so the safe-read profile is covered. The description adds that it returns open date windows and GuestHost booking links, which is useful output context beyond the annotations, but it does not explain any behavioral constraints like rate limits, auth needs, or why only one apartment is covered.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is short, front-loaded with the resource identity, and contains no filler. However, its extreme brevity for a tool with four undocumented parameters makes it feel under-specified rather than carefully concise.
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 four parameters, no output schema, and minimal annotations, the description is incomplete. It does not explain parameter usage, required versus optional inputs, or how the returned date windows should be interpreted, leaving significant gaps for an agent to fill.
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 four parameters and 0% schema description coverage, the description carries the full burden of explaining the inputs. It provides no meaning for 'guests', 'arrival', 'departure', or 'destination', leaving all parameters undocumented.
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 (a direct-bookable apartment in Milan) and what it returns (open date windows and booking links), but does not state a clear action verb like 'search' or 'list'. The name 'search_stays' suggests a broader search capability than the single-apartment scope described, and it does not differentiate this tool from the sibling 'get_booking_link'.
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 such as 'get_booking_link'. It does not mention prerequisites, required parameters, or scenarios that would select it over another tool.
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.
get_booking_linksearch_staysHoliday rentals booked direct with the host: availability, prices, checkout links. No auth.
Read-only property facts, indicative availability, authorised booking links and guest-safe support.
Airbnb stays by location and dates, and full listing details, as structured JSON.
Hosts: read and record bookings, change prices, draft listings, rename devices. No payments.
Add one secure layer between your agents and this server.
