list_foodsPaginated browse of FDC foods.
| Name | Required | Description | Default |
|---|---|---|---|
| sort_by | No | ||
| data_type | No | Filter to data type(s). Options: Branded | Foundation | Survey (FNDDS) | SR Legacy | Experimental | |
| page_size | No | 1-200 (default 50) | |
| sort_order | No | ||
| page_number | No | 1-based page |
| Name | Required | Description | Default |
|---|---|---|---|
| foods | No | Array of food items | |
| pageSize | No | Number of items per page | |
| pageNumber | No | Current page number |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, covering safety. The description adds 'paginated' but no further behavioral details (e.g., rate limits, data freshness). Value added is minimal.
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 sentence, front-loaded with the core purpose. No unnecessary words or redundancy.
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 the tool's simplicity (optional parameters, no required fields, output schema present), the description is mostly complete. However, it lacks clarification on sorting parameters and data type filtering options, which are present in the schema but not summarized.
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 60%, with descriptions for 'data_type', 'page_size', and 'page_number' provided in schema. The description does not add any parameter semantics beyond what is already in the schema, so baseline score of 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 clearly states the tool's action ('browse') and resource ('FDC foods'), with a distinctive feature ('paginated'). It is specific and distinguishes from sibling tools like 'search_foods' and 'get_food'.
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?
No usage guidance is provided. The description does not indicate when to use this tool versus alternatives such as 'search_foods' for filtered queries or 'get_food' for single item retrieval.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The tool set mixes USDA food data tools with a large number of unrelated tools (Polymarket betting, AI visibility, npm scanning, etc.), causing significant overlap in purpose. Many tools like ask_pipeworx, ask_pipeworx_grounded, deep_research, and bet_research all perform research/lookups with similar scopes, making it difficult for an agent to select the appropriate tool.
Tool names generally follow a descriptive verb_noun pattern (e.g., list_foods, search_foods), but there is inconsistency in prefixes (ask_pipeworx vs. pipeworx_feedback vs. polymarket_arbitrage) and some names are long and varied. The naming is readable but not highly predictable.
35 tools is excessive for a server ostensibly focused on USDA Food Data Central. Many tools are unrelated to food (e.g., Polymarket, Kalshi, npm scanning, subscription management), making the server feel bloated and unfocused. A typical food data server would have 5-10 tools.
For the USDA FDC domain, the tool surface is complete: it includes list, search, get, and nutrient retrieval. However, the presence of many unrelated tools dilutes the server's focus. The food-specific operations are well-covered, but the overall server lacks coherence.