Search hotels for a destination

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

With no annotations, the description carries the burden and does reasonably well: it discloses the return shape (ranked offers, per-vendor deal comparison, available_filters facet block, alternative_geos), the popularity-based geo resolution behavior, and the token tradeoff between concise and detailed formats. It omits auth requirements, rate limits, and whether the search hits live vendor APIs or cache, which keeps it from 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 short paragraphs, each front-loaded with the decision that matters most: what the tool returns, how to disambiguate the destination, then the verbosity knob. No filler sentences and no restatement of the name or title.

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?

For a 22-parameter tool with no output schema and no annotations, the description does the essential work of describing return values, the geo fallback loop, and the verbosity tradeoff. What remains thin is guidance on the large filter surface and any note about pagination or result-count behavior beyond the limit parameter.

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 baseline is 3; the description adds genuine value beyond it by spelling out the mutual-exclusivity constraint between destination and geo_id, the semantics of alternative_geos as a soft re-call hint, and the field-level difference between concise and detailed output. It leaves the filter parameters (amenities, lodging_types, price_range, etc.) to the schema, which is acceptable given full coverage.

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 — searching an aggregated hotel inventory across airbnb/expedia/google/kayak for a destination and date range — and distinguishes itself from siblings like wanderlog_search_places and wanderlog_add_hotel by naming the aggregator and vendor set. An agent can tell immediately this is the discovery tool for lodging offers, not trip mutation or generic place search.

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 explicit operational guidance: 'Specify exactly one of destination or geo_id', the fallback workflow of re-calling with a geo_id from alternative_geos when the wrong city is picked, and when to prefer response_format='detailed'. It does not name sibling alternatives (e.g. why not wanderlog_search_places or wanderlog_add_hotel), so it stops short of full when/when-not routing.

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