Adaga Network — Direct Booking Federation

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

With no annotations, the description carries the full burden and delivers: this is a mutation that creates a real, binding booking; it is not confirmed until card payment; unpaid bookings auto-expire; and it fails with HTTP 409 if the room became unavailable. These are exactly the side-effect, lifecycle, and failure-mode traits an agent needs before invoking a write 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?

Front-loaded with the core action before the numbered workflow, and every sentence carries operational content. It is dense with parenthetical asides, but nothing is filler; minor tightening is possible around the payment sentence.

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 mutation with no annotations and no output schema, the description covers the critical gaps: prerequisite search, required traveler data, payment/confirmation semantics, expiry, and the 409 failure case. It stops short of describing what the response returns beyond payment instructions and omits any authorization/tenant 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 coverage is 50%, so the description must compensate and largely does by naming the optional inputs (guests, phone, special_requests, breakfast, promo_code, extras ids) and framing which fields are collected from the traveler (full name, email). It adds meaning beyond the schema, though it does not clarify formats such as the shape of 'extras ids' or that 'phone' maps to the guest_phone field.

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 first sentence states a specific verb+resource ('Create a REAL booking at one establishment of the Adaga network') and the workflow immediately distinguishes it from network_search (read availability) and network_directory. An agent can tell what this tool does and where it sits in the sibling set without opening a 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 description gives an explicit 4-step workflow including the mandatory prerequisite (call network_search first for fresh availability and exact price) and the human-facing follow-up step (relay payment instructions). This is textbook when-to-use guidance with ordering constraints.

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. It discloses useful context — listings expose real-time availability and exact prices, there is no OTA commission, and coverage is currently hotels with salons/restaurants 'soon' — but says nothing about auth requirements, rate limits, or pagination for what could be a large directory.

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 tight sentences that front-load what the tool lists before describing usage. The parenthetical coverage caveat is mildly extraneous but carries real information about catalog scope.

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 must describe the return shape, and it does enumerate the key fields. For a zero-param read tool this is nearly complete; only auth and result-volume behavior are unspecified.

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 the baseline is 4. The description does add value by explaining the semantic role of the slug field as the key consumed by network_search and network_book, beyond what the empty schema conveys.

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 enumerates the identity fields returned (brand, type, city, slug). It is clearly distinct from the sibling tools network_search and network_book, which it names.

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 routes the agent: 'Use the slug for network_search and network_book,' establishing this as the discovery entry point that feeds the other two tools. It does not spell out when this tool is unnecessary or any prerequisites, but the chaining context is clear.

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 well: it discloses real-time availability, sorted-by-price output, a 6-second per-tenant timeout, and that non-responding tenants are skipped and reported in errors. It stops short of covering auth requirements or result-set size/pagination limits, so it is not fully exhaustive for a network-fan-out read 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?

Front-loaded with the core capability, then workflow, then constraints — a logical progression with no filler sentences. It is on the dense side, but every clause (price units, sort order, timeout, workflow steps) carries actionable 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 5-parameter search tool with no output schema, the description supplies the missing return-value context (availability + prices sorted, errors for skipped tenants) and the full calling workflow. An agent can execute the whole book flow from this 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?

Schema description coverage is 100%, so the baseline is 3. The description nonetheless adds semantics beyond the schema: the checkin < checkout and not-in-the-past constraints, the 30-night maximum, and the euro-cents unit for prices/budget, which help the agent form valid calls rather than just valid field 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?

States a specific verb+resource ('search the WHOLE Adaga network for a stay') with explicit scope (fans out to every matching establishment) and output characteristics (real-time availability, exact total prices in euro cents, sorted by price). The sibling tools network_book and network_directory are clearly differentiated — this one searches, the description even calls out network_book as the downstream step.

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 numbered workflow (call this, pick offer with tenant_slug + room_id, call network_book, hand payment instructions to the human) that tells the agent exactly when and how this tool fits into a larger task. Constraints (date format, checkin < checkout, no past checkin, max 30 nights) further delimit valid usage.

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