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

With readOnlyHint and openWorldHint already set, the description goes further: only discounts >=5% are kept, uncached cities are fetched live at most once per 6 hours, no-arg calls return one best per city, and a city call caps at 6 results. 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?

Three sentences pack the core purpose, filtering rule, argument-dependent behavior, caching, and a return-field note. It is dense but front-loaded with the most important verb+resource, and no sentence is filler.

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 three optional params, the schema descriptions, and the safety annotations, the description covers input modes, defaults and limiting, caching, and at least the key return field (booking_url). With no output schema, a fuller field-by-field return list would be nice, but nothing needed to invoke the tool correctly is missing.

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; the description adds value by specifying the no-argument world list behavior, the up-to-6 cap for city calls, the live-fetch/caching rule, and booking_url in results. It doesn't need to restate the schema.

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 a specific verb and resource ('List today's biggest observed hotel discounts') and immediately fixes the comparison method (Agoda live rate vs Agoda's own listed rate, 5% threshold). This is enough to distinguish it from siblings like search_hotels or list_tracked_hotels, even without naming them.

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 gives clear invocation context: omit arguments for the worldwide one-best-per-city list, pass city or city_id for up to 6 current deals, and city_id overrides city. It doesn't explicitly name sibling alternatives or state when not to use the tool, so it isn't a perfect 5, but the conditions are unambiguous.

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