Finish Gmail login (after browser approve)

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

No annotations are provided, so the description bears full responsibility for behavioral disclosure. It mentions that the tool 'waits if needed' and that 'no manual code copy required', but it does not disclose if the operation is destructive, read-only, or what happens on failure. It lacks details on authentication flow or prerequisites beyond browser approval.

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 short and front-loaded with the purpose, but it is too terse. While it wastes no words, it fails to include essential information about parameters and behavior, making it under-specified. Every sentence should earn its place, but the missing param info is a significant omission.

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?

Given the complexity (3 params with zero schema descriptions, no output schema, no annotations), the description is incomplete. It does not explain parameters, return values, error cases, or prerequisites beyond browser approval. The tool is part of a multi-account flow, but the description does not emphasize this context.

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 input schema has three parameters (code, pendingAlias, chatScope) with zero description coverage. The description does not mention any of these parameters or their purposes, leaving the agent completely in the dark about what values to provide. This is a critical gap.

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 clearly states the tool's purpose: to finish the Gmail login after browser approval. The verb 'Finish' and resource 'Gmail login' are specific. However, it does not explicitly differentiate from the sibling 'connect_finish' tool, though the 'multi' prefix implies multi-account context.

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?

The description provides explicit next steps ('After success, run `set_signer`, then `fetch`'), which guides the agent on what to do after using this tool. However, it does not mention when not to use this tool, nor does it explicitly state the prerequisite of having initiated the connection with a 'connect' tool first.

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