Sign-in link

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

Beyond the annotations (which only say readOnly=false, idempotent=false, destructive=false), it discloses the lifecycle: single use, 20-minute expiry, one sign-in, and that issuing a newer link replaces the old one — which explains the idempotentHint=false without contradicting it. It also tells the agent the sign-in happens on Uber's own page, so no credentials pass through the server, and prescribes how to relay the output.

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?

Front-loaded with what the link is, then its limits, then the call triggers — the ordering is sound and every clause carries information. The opening 'so this server can use it for them' is slightly convoluted, costing a small amount of clarity for a tool whose whole point is simplicity.

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?

With an output schema already covering the returned url shape, the description only needs to supply the semantics of the link — validity window, single use, replacement, per-caller scoping, and error-triggered invocation — and it supplies all of them. Nothing needed to call 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?

The tool takes zero parameters, so the baseline is 4 and there is nothing parameter-level for the description to clarify. It correctly directs all attention to the returned url rather than to 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 states a specific verb+resource: it produces a one-time sign-in link that lets the person authenticate to their own Uber account on Uber's own page. The mechanism, the scope ('for the calling person's account only'), and the fact that this server holds no credentials make it unmistakably different from data-returning siblings like uber_account or uber_trips.

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 names explicit triggers — a tool returning not_signed_in or session_expired, or the person asking to connect Uber — and adds a handling directive ('Give the person the url and nothing else'). There is no ambiguity about when to call it or what to do with the result.

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