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

Annotations already carry readOnlyHint and openWorldHint; the description adds genuinely new behavioral traits: an uncached city 'is fetched live at most once per 6 hours' (caching/freshness), a 5% discount filter, and a per-city cap of 6 deals. It doesn't describe the full response shape or city-mode sort order, but the added context is substantive.

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?

Four dense sentences, each earning its place: deal definition, worldwide mode, city mode with caching, and output fields. The methodology detail ('1-night stay about two weeks ahead (2 adults, USD)') is specific rather than padded, though the density makes it slightly heavy relative to a front-loaded one-liner.

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?

Covers both invocation modes, caching behavior, filter thresholds, and the key output fields (booking_url, image_url). With no output schema, the description could name the full response field set and city-mode ordering to be fully complete, but the deal-definition sentence implicitly carries much of the output semantics.

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?

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 today's biggest observed hotel discounts' — and goes further by operationally defining what counts as a deal: Agoda's live rate vs its own listed rate, 1-night stay two weeks ahead, 2 adults, USD, with a 5% discount floor. This precision distinguishes it from siblings like search_hotels (hotel search) and list_tracked_hotels (tracked hotels).

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 clear, actionable mode-based guidance: 'Without arguments, returns the single best deal per city' and 'With city ... or city_id, returns the current deals for that city (up to 6)'. It stops short of a 5 because it never explicitly names alternatives or when-not-to-use conditions relative to siblings.

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