post_data_hotel_highlights

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

Strong disclosure beyond the annotations: 10 req/min rate limit with the exact 429 failure, server-side resolution of hotel facts from hotelId, graceful degradation to 200 with template highlights and generated:false, and caching of identical request bodies. The caching claim sits in mild tension with idempotentHint=false and the generation-oriented readOnlyHint=false, but the description never contradicts the annotations outright and instead supplies the observable behaviour an agent needs.

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?

The markdown headers (Overview, When to Use, What You Get, Behaviour) make it scannable and the beta/rate-limit warning is front-loaded. It is longer than strictly necessary and repeats a couple of points between 'What You Get' and 'Behaviour', but nearly every sentence carries usable information.

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 correctly carries the return-value burden: exactly count highlights, the echoed type field, and the generated flag distinguishing AI copy from template fallback. Combined with rate-limit, fallback, and caching behaviour, an agent has everything needed to call this tool correctly and interpret the response.

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 description coverage is already 100%, so the baseline is 3, but the description adds response-mapping semantics not present in the schema: 'type' is echoed back so cards can be mapped to a UI, exactly count highlights are always returned in order, and highlights entries are treated as topic guidance only (unsupported claims are not invented). That clarifies how inputs shape outputs, which the schema alone does not.

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 action and output artifact: generate short AI-written 'Smart Highlight' cards (title + one or two sentence description) for a hotel, in a requested language. This is clearly distinguishable from sibling tools like get_data_hotel, get_data_hotel_ask, or get_data_reviews, which retrieve factual content rather than generate copy.

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?

The 'When to Use' section gives concrete surfaces (hotel detail pages, partner-specific tone via tone/style/per-highlight context), which is stronger than most definitions. It does not, however, name any alternative tool or state when NOT to use it (e.g., when plain factual hotel data is wanted), so it falls short of explicit routing guidance.

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