swiggy_collections

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

With no annotations provided, the description takes on the burden of behavioral disclosure. It goes beyond the schema by explaining the is_serviceable field and the nuanced interpretation of an empty list (it can be a coverage answer rather than a genuine lack of collections). This gives the agent essential behavioral context, though it doesn't explicitly mention read-only or rate limits, which are less critical for a list endpoint.

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 compact, with the main purpose front-loaded in the first sentence. The second sentence adds why this tool is used (identifying collection ids for swiggy_search), and the third addresses an important edge case. Each sentence contributes to understanding the tool, so the length is justified.

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?

Given there is no output schema, the description does a solid job of covering the main aspects: the return type (curated collections), an important field (is_serviceable), and the behavioral nuance around empty results. It also ties into the downstream search tool. It stops short of describing the full object structure of a collection (e.g., id and name), but that level of detail is not strictly required for selection and invocation.

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?

The input schema already provides complete coverage for the two parameters, latitude and longitude, with matching descriptions. The tool description only restates that it takes a latitude/longitude, adding no additional semantics such as format, range, or required precision. With 100% schema coverage, the baseline of 3 is appropriate; the description doesn't add meaning beyond what the schema provides.

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 opens with a clear imperative verb 'List' and identifies a specific resource ('Swiggy's curated collections') with a clear location scope (latitude/longitude). It differentiates the tool from swiggy_search by explaining that collection ids feed into swiggy_search's collection_id parameter, and it gives concrete examples of what the collections are. This is more than a mere restatement of the name; it lets an agent know exactly what the tool returns and how it relates to a sibling.

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 the usage context: you need to retrieve curated collections for a location before browsing restaurants within a collection, and it explicitly routes the agent to swiggy_search for that next step. It doesn't explicitly state 'when not to use' the tool versus alternatives, but it does communicate a clear use case and connects to a sibling. This is above the threshold of mere 'clear context, no exclusions'.

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