SMART discover

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

With no annotations, the description carries the full burden of behavioral disclosure. It includes one genuinely useful behavioral note ('Does not invent endpoints'), signaling the tool only returns what the server actually advertises. However, it omits other relevant behavior such as error handling when iss is not allowlisted, whether authentication is needed, or any required scopes, leaving the behavioral profile only partially disclosed.

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?

Three terse, information-dense sentences with no filler. The endpoint is front-loaded, followed by the spec version, the parameter constraint, and the single most important behavioral caveat. Every sentence earns its place.

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 simple one-optional-parameter discovery tool with no output schema, the description covers the endpoint, the constraint, and the key behavior. Return format is not described, but SMART discovery responses are standardized by the cited spec, reducing the need. Only edge-case behavior (unallowlisted iss handling) is left unspecified, which is minor for this tool's simplicity.

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 coverage is 0%, so the description must compensate. It does add meaning by substituting iss into the URL path and by stating the v1-allowlist constraint. However, it never explicitly defines iss as the FHIR server base URL or describes the valid format/value domain beyond the allowlist, leaving some semantic burden on inference from the '{iss}' placeholder.

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?

States a specific verb (GET) plus a concrete resource (.well-known/smart-configuration) with a spec version (SMART App Launch 2.2.0). The '{iss}' prefix clarifies it targets a specific FHIR server's discovery document, and it is clearly distinct from the sibling tools (fhir_auth_status, fhir_search, fhir_read) which handle auth status and searches/reads rather than capability discovery.

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?

Provides a useful precondition (iss must be v1-allowlisted) and clarifies the call is optional-parameter. However, it gives no explicit guidance on when to prefer smart_discover versus sibling tools like fhir_auth_status, nor any exclusion criteria. The 'when to use vs alternatives' context is implied by its distinct purpose but never stated.

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