Advanced product search

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, covering the safety profile. The description adds the 'fuzzy search' behavioral trait, which is useful. However, it does not disclose what happens when no query is provided, whether results are limited to promotions or include all products, or the response format/pagination behavior beyond the schema. No contradiction with annotations.

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 a single, information-dense sentence that front-loads the core action ('Fuzzy search and browse promotions') and lists the filter dimensions without unnecessary words or repetition. Every phrase contributes value, making it highly efficient for an agent 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?

For a tool with 12 parameters and no output schema, the description provides a sufficient overview for selecting the tool, but lacks commentary on the return shape, default behavior when no parameters are supplied, and the specifics of fuzzy matching. Annotations cover safety, but the description does not fully compensate for the absent output schema and low parameter description coverage.

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 only 25%, so the description helps by enumerating filter categories (status, type, price, savings, sorting) that map to specific parameters. Yet it does not explain the search term q, acceptable values for sort_by or promotion_type, or the meaning of 'type' beyond the parameter name. It partially compensates for the schema's lack of descriptions but leaves several parameters semantically vague.

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: 'Fuzzy search and browse promotions' with a specific list of filters. It distinguishes itself from siblings like list_products or search_products_by_name by emphasizing fuzzy matching and a wide range of filter dimensions (retailer, category, status, type, dietary, price, savings, sorting, pagination). The title 'Advanced product search' reinforces this differentiation.

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 a use case—searching products/promotions with complex filters—but does not explicitly state when to use this tool versus alternatives such as search_products_by_name or get_promotional_products. There are no exclusions, prerequisites, or direct references to alternative tools, so the agent must infer applicability from the filter list.

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