US Government Open Data MCP

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

No annotations are provided, so the description carries the full burden. It discloses key behavioral traits: it's a search operation (implying read-only), returns specific fields (device class, product codes, definitions), mentions the dataset size (~1,700 types), and includes count fields. However, it lacks details on error handling, rate limits, authentication needs, or pagination behavior beyond the 'limit' parameter. The description doesn't contradict any annotations (none exist).

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 highly concise and well-structured. The first sentence states the purpose and scope. The second lists return values. The 'Example searches' section efficiently demonstrates usage with four varied examples. The final note on count fields is brief and relevant. Every sentence adds value with zero wasted words, and key information is front-loaded.

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 moderate complexity (search with two parameters), 100% schema coverage, and no output schema, the description is largely complete. It covers purpose, usage examples, return values, and dataset context. The main gap is the lack of output structure details (e.g., response format), but this is partially mitigated by the examples implying a list of results. For a search tool without annotations, it provides sufficient context for effective use.

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 100%, so the schema fully documents both parameters ('search' and 'limit'). The description adds significant value beyond the schema: it provides concrete examples of search queries (e.g., 'regulation_number:872.6855'), explains the meaning of device class codes (1=Class I, etc.), and mentions count fields. This contextualizes the parameters effectively, though it doesn't detail advanced query syntax beyond the examples.

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 purpose: 'Search medical device classification — ~1,700 generic device types. Returns device class (1=Class I, 2=Class II, 3=Class III), product codes, definitions.' It specifies the exact resource (medical device classification database), the verb (search), and the return values. This distinguishes it from all sibling tools, which cover entirely different domains like economic data, legislation, or other FDA datasets.

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 context for usage through multiple example searches (e.g., by regulation number, product code, device name, device class). It implicitly guides the user on how to structure queries for different use cases. However, it does not explicitly state when to use this tool versus alternatives (e.g., other FDA device tools like fda_device_510k or fda_device_recalls), nor does it mention any prerequisites or exclusions.

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