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

Annotations already establish readOnly/idempotent/non-destructive safety, and the description adds valuable behavioral context beyond that: 'Returns offers + min/median' discloses the output shape, and 'Fee coverage differs per platform — compare on totalPrice' warns about a cross-platform inconsistency. It also explains that the tool either resolves via Google or prices provided listings directly, which is a notable operational behavior. No contradiction with annotations.

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 two sentences and approximately 60 words. The first sentence is a crisp purpose statement, and the second packs mode guidance, output summary, and a key caveat without redundancy. It is front-loaded and every clause earns its place.

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?

The tool has 10 parameters, no output schema, and two modes, but the description covers the essential context: purpose, mode selection, return values, and an important fee-cover caveat. It doesn't enumerate every parameter (schema partially does), and it omits details like input validation/error behavior, but for a comparison tool this is a strong, nearly complete description.

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 only 50% schema description coverage, the description compensates by mapping parameters to modes: name/location/googleHotelId are grouped as the Google-resolve path, and listings is explained with format examples ('platform:listingId'). It also clarifies that listings mode is for known-same properties and adds the totalPrice comparison caveat. However, it leaves checkIn/checkOut/currency semantics to the schema (which lacks descriptions for them), so it doesn't fully complete the parameter picture.

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 opens with 'Cross-OTA price comparison for one property,' a specific verb+resource statement that clearly distinguishes this from siblings like get_price (single price) and check_availability. It further details two distinct operational modes (Google-resolved vs. direct listings), leaving no ambiguity about what the tool does.

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 explicit guidance on choosing between the two modes: 'Either let Google resolve it (name / location / googleHotelId), or pass listings=...' and clarifies when direct listings are appropriate ('for listings you already know are the same property'). It also advises on interpreting results ('compare on totalPrice'), but it does not explicitly reference sibling tools or state when to prefer this over get_price/check_availability, so it misses the top bar.

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