find_duplicate_products

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

With no annotations, the description carries the full burden, and it succeeds. It reveals that the tool only reports clusters, suggests a canonical listing based on ACTIVE + QC APPROVED on any business client with oldest winning, and explains the expensive full-scan behavior. It also warns that Jumia has no merge endpoint, which prevents the agent from expecting one.

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 dense but mostly front-loaded: the first sentence states the core purpose, and subsequent sentences add caveats and usage context. All sentences carry useful information, though the middle sentence is long and could be cleaned up, so it does not quite earn a 5.

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 behavior, canonical-listing logic, and cost trade-off are well covered, and the mention of 'reports clusters' gives some idea of the output. However, with no output schema and several undocumented parameters, the description leaves gaps about the exact return shape and the meaning of max_products_scanned and name_similarity_threshold.

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 0%, so the description must compensate, but it only explains category_code. The other parameters (shop_id, max_products_scanned, name_similarity_threshold) are left entirely to the agent's inference from names and schema defaults, which is insufficient for a tool with four unrestricted parameters.

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 specific verb and resource: 'Flag products that look like the same real-world item listed more than once', then details exact matching criteria (GTIN/EAN/barcode or brand+category+images near-identical name). It also distinguishes itself from deactivate_products by explicitly stating it only reports clusters and that deactivation is a separate later step.

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 provides clear practical guidance: narrow with category_code for large catalogs, and warns that a full paginated scan is expensive across multi-country catalogs. It notes there is no merge endpoint and that resolution happens via deactivate_products, giving a workflow direction, though it does not explicitly contrast with sibling tools like find_outdated_products or list_products.

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