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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond annotations: this is a polling operation that must be retried, and completion must come from the browser flow rather than user-supplied tokens or a 'done' message. It doesn't discuss timeouts or rate limits, but the presence of an output schema and the simple read-only nature make that gap minor.

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 with no wasted words. The critical relationship to ucode_login_start is front-loaded, followed by the repeated-polling instruction and the guardrail about not relying on user tokens or 'done'. Every sentence 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 single-parameter, read-only polling tool with an output schema, the description provides the essential flow context: when to call it, that it must be called repeatedly, and that the completion signal should come from the browser flow. Nothing material is missing for correct invocation.

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 description coverage is 100%: the only parameter, sessionId, is already described as 'sessionId returned by ucode_login_start' with a minLength constraint. The tool description adds no further parameter-level detail, so the baseline of 3 applies since the schema carries the load.

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 uses a specific verb ('Poll') and resource ('after ucode_login_start'), states the outcome ('Links the ChatGPT session when the user has finished in the browser'), and is clearly differentiated from its sibling login_start by naming it as the prerequisite. The title 'Finish browser sign-in' reinforces the intended phase.

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 explicitly says when to use this tool ('after ucode_login_start'), how to use it ('call repeatedly until complete'), and what not to do ('do not ask users to paste tokens or to type “done” as the only completion signal'). This gives the agent concrete invocation guidance and avoids common failure modes.

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