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

Annotations only cover the safety profile (readOnly=false, idempotent=false, destructive=false); the description supplies the operational behavior annotations cannot express: the call returns a URL the user must open out-of-band, the user must copy a 'code' from the address bar, and a second tool call completes the flow. The only arguable tension is that openWorldHint=false while the flow involves Google/Apple sign-in, but that interaction happens outside the tool, which itself only mints a URL.

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?

Four short sentences, each doing distinct work: purpose, exclusion, return-and-continuation mechanics, and per-restaurant scope. The key fact (returns a URL, follow up with submit_login_code) is front-loaded in the third sentence with no filler.

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?

There is no output schema, and the description compensates by describing exactly what the call returns (a URL) and what the agent must do with it. Combined with the per-restaurant scope and the named follow-up tool, an agent has everything needed to run the full login flow correctly.

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 100% and the single clientId parameter is already fully documented in the schema (including the omit-when-single-restaurant case). The description reinforces why a restaurant must be identified ('each restaurant has its own login'), which is mildly useful context but mostly restates the schema rationale, so the baseline 3 applies.

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 and resource ('Start signing the user in to a restaurant') plus the goal ('so they can place orders'). It explicitly carves out the sibling boundary — browsing the menu never needs this — so an agent can rule it out without inspecting other schemas.

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 explicit when-to-use (ordering, saving an address), explicit when-not (browsing the menu), and names the follow-up tool (submit_login_code) that must be called afterward. It also states the per-restaurant constraint that governs when the tool applies at all.

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