Adaga Network — Direct Booking Federation

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

With no annotations provided, the description carries the full burden and delivers: the booking is confirmed only after secure card payment, unpaid bookings expire automatically, and the call fails with 409 if the room became unavailable. These are exactly the lifecycle and failure-mode facts an agent must know before committing a real booking.

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 action statement is front-loaded, the workflow is numbered, and the optional-input list is compact. It is slightly long, with some optional-parameter prose that partly duplicates the schema, but nearly every sentence supplies decision-relevant information.

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

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

For a 12-parameter, no-output-schema mutation tool, the description covers prerequisites, required traveler data, failure mode, and the payment-confirmation lifecycle, and even notes that payment instructions come from the response. It stops short of describing the rest of the response body or permission/authentication requirements.

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 100%, so the baseline is 3, but the description adds meaning beyond the schema: guest_phone is illustrated with a concrete international-format example, extras are tied to the establishment offer, and promo_code is flagged as validated by the establishment. Minor remaining gap is that guests/breakfast constraints are only restated.

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 ('Create a REAL booking at one establishment of the Adaga network') and the word 'REAL' plus the follow-up workflow makes clear this is the commitment step, not the discovery step. An agent can distinguish it from network_search (availability) and network_directory without opening any 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?

Gives an explicit numbered workflow: call network_search first for availability and price, collect name/email, call this tool, then relay payment instructions. It also states the precondition (fresh availability) and the required inputs to gather, leaving no ambiguity about when and how to invoke it.

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 behavioral burden and does so: no authentication required, no rate limit, no pagination, complete directory returned in one response. It also discloses the critical downstream constraint that 'listed' establishments are NOT bookable here despite appearing in the roster, which prevents a costly misinterpretation.

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 definition is front-loaded, with the roster scope and tier semantics before the alternative-tool routing. However, the OTA-commission passage ('OTAs take 15-25% AND own the customer') is business/marketing framing that does not change how an agent invokes the tool and dilutes an otherwise dense, information-rich description.

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 the return payload, and it does: the tier field, its two possible values, and the fields available for listed entries (name, address, phone, official website). An agent has everything needed to call it and interpret the response without further documentation.

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 takes zero parameters, so the baseline is 4 and there is nothing for the description to disambiguate. It does usefully explain that the returned slug is the key accepted by network_search and network_book, which is a value-level detail rather than a parameter one.

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 ('List every establishment in the Adaga direct-booking network') and immediately scopes it against siblings by naming network_search as the date-aware alternative. The tier taxonomy ('verified' vs 'listed') further clarifies what kind of entries the tool returns, which an agent needs to interpret the result set.

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

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

Explicitly states when to use this tool versus network_search ('use this tool when you need the full roster or an establishment's slug') and explains that network_search should be used when stay dates are known. It also names the downstream tools that consume the returned slug (network_search, network_book) and conditions the latter on verified tier.

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 and does so thoroughly: live real-time availability, price unit (euro cents), sort order, exact direct prices with no OTA markup, the 6 s per-tenant timeout with skipped tenants reported in errors, and explicit 'no authentication, no rate limit, no pagination' guarantees. It also discloses that listed_matches are public website/phone data and not bookable here.

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?

Dense but appropriately sized for a multi-mode, no-annotation tool; the core purpose is front-loaded before the workflow and constraints. Slightly bloated by marketing framing ('like Booking.com but machine-native') and some parenthetical restatement, but nearly every clause carries operational information.

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

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

With no output schema, the description still explains the return shape (verified offers plus an appended listed_matches array) and how matches are ordered. Combined with the constraints, timeout behavior, and auth/rate-limit disclosures, an agent has everything needed to call this 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 100%, so the schema documents all five parameters and the baseline would be 3. The description adds meaning beyond the schema though: the YYYY-MM-DD format, the cross-field constraint checkin < checkout, the prohibition on past check-ins, the 30-night cap, and the euro-cents unit for budget/prices.

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 ('Search the WHOLE Adaga network ... for a stay') and immediately distinguishes the two result classes (verified, bookable offers vs. listed_matches that are NOT bookable). An agent can tell this apart from network_directory and network_book without opening any 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?

Provides an explicit ordered workflow (search → pick tenant_slug + room_id → network_book → hand payment instructions to human) and names the alternative tool with the condition that selects it ('Use network_directory instead when you need the full roster without stay dates'). Nothing is left to inference.

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