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

Annotations already declare readOnlyHint=true, and the description adds substantial behavior beyond that: it returns only catalog fields (name, address, stars, rating, review count), never prices, resolves the city to 'the best catalog match', and surfaces other_city_matches when several cities match. These traits — catalog-only, no-pricing, ambiguity handling — are not visible in the schema or 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?

Four sentences, each carrying distinct weight: purpose, exclusions/alternatives, parameter usage, and ambiguity handling, with the core purpose front-loaded. It is slightly longer than strictly necessary because the multi-language input hint partly duplicates the schema examples, but nothing is wasted.

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 no output schema, the description compensates by naming the returned fields and the other_city_matches disambiguation field, and it explicitly rules out prices so an agent won't expect pricing data. The only gap is unspecified behavior when no city or hotel matches, but for this complexity level the coverage is strong.

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 real value on top: multilingual input support ('Korean, Japanese, Chinese or English'), the trigger condition for the hotel filter, and a concrete disambiguation flow for city_id. The only redundancy is that the schema examples already illustrate the multi-language city forms.

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 — 'Resolve a hotel to the agoda_hotel_id that track_hotel_price needs' — giving the tool a crisp identity. It further distinguishes itself from siblings with 'not a hotel search engine' and 'no prices — for prices, track the hotel or use list_hotel_deals', so an agent can tell it apart from the price-focused tools in the sibling list.

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?

Explicitly routes between alternatives: lookup/ID resolution here, prices via track_hotel_price or list_hotel_deals, and gives the canonical workflow 'search_hotels → track_hotel_price → get_price_history'. It also conditions parameter usage ('when the user named a hotel, the hotel filter') and explains the city_id override path for ambiguous matches.

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