scrape_zomato

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

With no annotations, the description carries the full burden of behavioral disclosure. It explicitly states network access ('Requires outbound network access'), live data variability ('results reflect live Zomato data at call time and may vary between calls'), and edge-case behavior ('Returns an empty list if the city is unknown'). It does not mention rate limits or potential blocking, but the disclosed behavior is substantial and helpful for an agent.

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 description is concise, front-loaded with the core purpose, and every sentence adds value. It covers purpose, method, filters, output format, ordering, caps, edge cases, and network dependency without unnecessary fluff. It is well-structured and easy to parse.

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?

The description provides a complete picture for a scraped-list tool: it states what it does, how it works (network scraping), what output to expect (dict list with example fields, ordering), how to control result count (max_results), and failure modes (unknown city, no matches). Given 3 parameters and no output schema shown, this is sufficiently thorough for an agent to invoke correctly.

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 meaningful context beyond the schema: query is described as 'a cuisine or name term' and max_results is described as capping the list. It also clarifies the output structure (list of dicts with example fields), which indirectly informs parameter meaning. This exceeds baseline.

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 clearly states the tool's function: 'Search Zomato for restaurants in a city and return a list of restaurant records.' It uses a specific verb (search/scrape) with a specific resource (Zomato restaurants) and highlights distinct features like city-based search and optional filters. This distinguishes it from sibling tools such as scrape_url or search_ubereats.

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 description implies usage context ('Search Zomato for restaurants in a city') but does not explicitly mention when to use this tool versus alternatives or provide exclusion criteria. It lacks statements like 'for restaurant listings from Zomato, use this' or 'not for other food delivery services.' No alternatives are referenced, so guidance is only implied.

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