Connect sundhed.dk

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

The description is transparent about opening a browser, waiting up to 3 minutes, and returning a link on hosted servers, which goes beyond the sparse annotations. However, it contradicts the readOnlyHint: true annotation by describing an action that starts a login and solicits user credentials, which is a state-changing interaction rather than a read-only operation. Per the scoring rule, this is an annotation contradiction and receives 1.

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 compact and front-loaded: the first sentence states the purpose, and the following sentences supply necessary procedural details for both deployment modes. No sentence is filler; the closing usage rule 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 no-parameter, no-output-schema tool, this description covers the key operational details: what the tool starts, how it behaves locally vs hosted, how long it waits, and what the agent should tell the user. It doesn't specify the return value or failure behavior, but those are less critical because the next step is presumably to check session_status.

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 tool has zero parameters and the schema already fully covers this (100% coverage), so the description has no parameter semantics to add. The baseline for zero-parameter tools is 4, and the description does not introduce any confusion about inputs.

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 names a specific verb and resource: it starts a sundhed.dk login via MitID. This is clearly distinct from the sibling get_* tools and from session_status/disconnect_sundhed, so an agent can identify its role immediately.

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?

It gives an explicit trigger: 'Call this when another tool says the person is not logged in.' It also adapts guidance for local and hosted environments, so the agent knows what to relay. It does not state a when-not condition or name alternative tools, but the usage context is clear.

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