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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds meaningful context on top: the result is a multi-seller list including the hotel's own site, each entry carries a stay total and a link that leaves the app to open the seller's checkout — which is exactly the openWorld behavior an agent should anticipate. It does not mention auth requirements or result limits, so it stops short of a 5.

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 sentences, each load-bearing: trigger, payload description, input provenance, then the sibling exclusion. The purpose and the 'when' are front-loaded before any detail.

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 an output schema present the description need not explain return fields, yet it still characterizes the result well enough to set expectations. Trigger, inputs, provenance, and sibling differentiation are all present for a simple two-parameter read 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 100% and both properties are already documented as coming from search_hotels, so the description's 'Takes the search_key and hotel_id from search_hotels' largely repeats the schema. Baseline 3 is appropriate when the schema carries the parameter burden.

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 a specific action (retrieve every seller quoting a given hotel for the searched dates), the resource (hotel booking sellers), and the payload shape (stay total plus a checkout link per seller). It also distinguishes itself from the near-named sibling booking_options and from track_hotel by explicitly disclaiming price watching.

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?

It opens with an explicit trigger ('Use when the traveler wants to book a hotel from search_hotels'), states the prerequisite source for both inputs, and names an exclusion ('Not a price watch (track_hotel)'). An agent knows both when to call it and when not to.

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