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

readOnlyHint=true already establishes the safety profile, so the bar is lower; the description adds the content scope of the response (resources, interactions, search parameters) and the diagnostic use case. It does not mention auth requirements or response size, but for a read-only metadata endpoint this is reasonably complete.

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?

Two sentences, front-loaded with the resource and scope, followed by the trigger condition and the raw endpoint. No filler; every clause carries information.

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 parameterless, read-only metadata tool with no output schema, the description covers what is returned, when to call it, and the underlying endpoint. Nothing an agent needs to invoke it correctly is missing.

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?

Zero parameters, so the baseline of 4 applies; there is nothing for the description to disambiguate. The inclusion of the raw endpoint path (GET /metadata) is a minor bonus rather than required semantics.

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?

Names a specific verb and resource (Fetch the server's FHIR CapabilityStatement) and immediately scopes it: exactly which resources, interactions and search parameters this Canvas instance supports. That distinguishes it from the read/search/everything siblings, which operate on clinical data rather than server metadata.

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?

Gives a concrete activation condition: 'Read it when a search is rejected and you want to know what the instance actually accepts.' That is a clear when-to-use signal, but it names no alternative or when-not-to-use condition.

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