Taste Overlap

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

With no annotations, the description carries the full burden and delivers real behavioral detail: results come from Qloo's taste graph, the cap is six, each pick carries a reason, results are sequenced for an evening (activity, food, drink), and basis=combined is explained as a fallback when the two personal top-20 lists under-overlap. It stops short of disclosing latency, auth, or failure modes for an unknown city.

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?

Two sentences, front-loaded with the input contract before the output semantics, and every clause adds usable information (count, ranking, reason, ordering, fallback basis). It is dense and slightly run-on, but there is no filler to cut.

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 and no annotations, the description fully covers the return contract (six places, reason per place, evening order) and the ranking/fallback logic behind it. Only edge behavior — e.g. what happens for an unrecognized city or how ties are broken — is left unaddressed.

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 3 is the baseline, but the description adds genuine meaning beyond the schema's generic 'Favourites of person A': it enumerates acceptable favourite types (artists, films, shows, books, brands) and clarifies the input is 'a few' per person, matching the maxItems=5 constraint.

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 names a specific verb and resource ('returns up to six places both would enjoy') and fully specifies the output shape: count, ranking source, per-item reason, and evening ordering. It is impossible to confuse this with anything else, and no sibling tool needs to be named.

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?

Usage is only implied by the input contract ('Given a city and a few favourites for each of two people'), which tells the agent the required context but gives no explicit when-to-use, when-not-to-use, or alternative tools. With no siblings listed there is nothing to route against, so this is adequate rather than strong.

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