hemmabo_booking_negotiate

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false, and the description goes far beyond them: it thoroughly discloses non-idempotence (each call writes a new snapshot, re-locking returns a new quoteId), the fixed validUntil that never extends, the channel selection behavior in checkout, and the explicit rule that the quoteId is only redeemable for identical inputs. It also admits what the tool does NOT do (never bargains, discounts, or alters the price). This matches annotations and adds substantial behavioral context.

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 dense and front-loaded with the most critical fact (the tool is a lock, not a negotiation). Every sentence adds behavioral or routing value, with no fluff. However, it is quite long for a tool description and could be slightly trimmed without losing substance, so it's not a perfect 5. The length is justified by the complexity of the behavioral rules, so it earns a 4.

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 tool's complexity (non-idempotent, time-limited, channel-dependent) and the rich input/output schemas and annotations, the description is remarkably complete. It covers what the tool does, when to use it, what it refuses to do, the locking mechanics, the redemption constraints, and the exact conditions for reproducibility. The output schema exists, so return values are covered elsewhere, and nothing critical an agent needs to invoke it correctly is missing. The description fully compensates for the tool's complexity.

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 meaningful value on top: it explains that 'night count and guest count together select the locked price tier', clarifies that checkIn/checkOut define the stay length 'used for pricing and availability', and frames guests as tier-determining. It also reiterates the requirement to pass the exact property UUID. This goes beyond what the schema alone provides, though it doesn't add syntax details for each parameter. Given full schema coverage plus additional tier/price context, a 4 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 is exceptionally explicit: it begins by reframing the tool's name ('PRICE LOCK, not negotiation'), names the exact verb (freezes a price for 15 minutes), the resource (current host-source price), and the scope (only in the non-VRP fallback checkout flow). It clearly distinguishes itself from get_verified_stay_offer and other siblings, and its title 'Lock Price Quote' is consistent, so there's no ambiguity about what action this tool performs.

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 explicit, precise usage instructions: use only in the non-VRP fallback checkout flow, only when no signed direct_booking_url is available, and only when the user explicitly requests to lock a price. It also names exclusions and the alternative tool (get_verified_stay_offer), and lists many contexts to avoid (search, availability, VRP offers, rendering a stay-offer widget). This is essentially a perfect usage-guide.

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