fhir_search

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

With no annotations, the description discloses key behavioral details: it returns a raw Bundle (first page only) and instructs to follow Bundle.link[next] for pagination. This goes beyond the schema and gives the agent a realistic expectation of the output. It does not mention auth or error handling, but for a search operation this is relatively transparent.

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 two sentences, with the core action front-loaded ('Search any FHIR resource type') and a concise, valuable note about the response format and pagination. There is zero filler, making it highly efficient.

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 description covers the core purpose, return type, and pagination, but it lacks crucial guidance on parameter construction and prerequisites like a connected practice. For a generic search tool with three params and no output schema, the missing param semantics leaves the agent under-informed, making it only somewhat complete.

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 schema has no descriptions for practice, resource, or params, and the description provides minimal additional meaning. 'Arbitrary query params' is vague; it doesn't explain how to structure the params object (e.g., key-value FHIR search parameters), what resource values are valid, or how practice is used. With 0% schema coverage, this is a significant gap.

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 with a specific verb and resource: 'Search any FHIR resource type with arbitrary query params.' It distinguishes itself from sibling tools by covering all resource types generically, unlike specialized search tools like search_encounter or fhir_get.

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 generic usage applicable to any FHIR resource, which indicates when to use this tool over specialized alternatives. It also provides pagination guidance ('follow Bundle.link[next] for more'), offering clear context. However, it does not explicitly exclude cases where specialized search tools should be used.

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