login_start

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

With no annotations, the description carries the full load and does disclose real behavior: the result is a QR image plus a short-lived link, the link is sensitive and may leak into client logs, and replace_existing has a consequential effect that needs approval. It stops short of stating what replace_existing actually invalidates (an existing session/token) or any rate limits.

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 compact sentences, zero filler, with the primary action and the returned artifact front-loaded ahead of the security caveat. Every clause carries information an agent needs.

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 one-optional-parameter tool with no output schema, the description covers the return shape and the sensitivity of the credential material, which is the hard part. The remaining hole is lifecycle: nothing tells the agent that the login must subsequently be polled or cancelled via its sibling tools.

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 and does: 'short-lived' and 'Set replace_existing only with approval' imply the flag discards an existing login session and should not be flipped casually. It still never says what gets replaced or whether the old session is invalidated, so meaning is added but not fully pinned down.

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 gives a specific verb and resource ('Start login') and, unusually, states the return payload ('a QR image plus its short-lived link'), which separates it from a bare status check. It never names qr_login_status or qr_login_cancel, so differentiation from those siblings rests on the name alone rather than on the text.

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?

Usage is only implied: an agent infers it should call this when a login is needed, and the description never says to follow up with qr_login_status to poll for completion. The only explicit guidance is a parameter-level caution ('Set replace_existing only with approval'), which is a prerequisite rather than a when-to-use rule.

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