List Categories

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

With no annotations provided, the description must disclose behavioral traits. It indicates the tool fetches categories for a site, implying a read-only operation, but does not explicitly state that it is safe or non-destructive. It does not disclose potential rate limits, authentication requirements, or what happens if the site_id is invalid. It also does not describe the structure of the response beyond the mention of 'top-level categories'. Given zero annotations, the description carries a moderate burden but does not meet it fully, hence a 3.

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, with a single sentence stating the purpose, followed by two bullet-point usage examples. It is front-loaded with the core function and then provides concrete mappings. The structure is efficient, but the usage examples could be considered redundant with the schema's parameter descriptions. Overall, it is well-sized and structured, earning a 4.

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 tool is relatively simple (listing categories) with an output schema available, so the description need not detail return values. However, it lacks guidance on error scenarios (e.g., unauthenticated sites, invalid site_id) and does not mention that the account parameter is optional or how authentication factors in. Given the context signals (only 1 param, output schema exists), the description is adequate but not complete for an agent to handle edge cases, so a 3 is fair.

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 has 0% description coverage, meaning parameter descriptions in the schema are present but only the descriptions in the JSON schema are used; however, the schema does include detailed descriptions for 'account' and 'site_id', which explains their purpose and defaults. The tool description's usage examples add meaning by linking site_id to specific countries (e.g., MLA=Argentina), which is not in the schema. This compensates slightly, but the description itself does not elaborate on parameters beyond the examples. Since the schema provides decent parameter documentation via its own descriptions, a baseline 3 is appropriate.

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 states the tool's purpose clearly: 'Get all top-level categories available on a MercadoLibre site'. It identifies a specific verb ('Get'), resource ('top-level categories'), and scope ('available on a MercadoLibre site'). It distinguishes from siblings like get_category (which fetches a single category) and predict_category (which predicts a category), though it does not explicitly name these alternative sibling tools. The usage examples provide concrete mappings from natural language to the site_id parameter, which aids selection.

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: it is for listing top-level categories, not for searching items or predicting categories. The examples ('What categories are available in Argentina?' → site_id=MLA) show when to use it, but there are no explicit exclusions or guidance on when not to use it versus alternatives. It relies on the context signals and sibling tool names to infer the boundary, which is reasonable but not fully explicit.

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