Completes the connection after you approve the browser link, saving the token locally. Returns pending until approval, so check no more than once every 5 seconds.
After the user approves the browser link, finish the connection. Token is saved locally, never returned in tool output. Pending means the user has not approved yet; do not poll faster than once per 5 seconds.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations, it discloses that the token is persisted locally and never returned in output, and that a 'pending' result means the user has not yet approved — both non-obvious behaviors. It does not address idempotency of repeated calls or error/expiry behavior, and given destructiveHint=true it says nothing about what a failed or repeated finish does to existing credentials.
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 short sentences, each carrying distinct load: the action, the security-relevant output behavior, and the state/polling semantics. Nothing is repeated and the triggering condition is front-loaded.
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 no parameters and no output schema, the description covers the essentials an agent needs to call it correctly and interpret a pending result. The remaining gap is failure handling and the destructive implications flagged by annotations, which the description leaves unaddressed.
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. The description correctly implies all context comes from prior approval state rather than arguments, adding nothing misleading about 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 uses a specific verb+resource ('finish the connection') and ties it to the approval step of a browser link flow, so the agent can distinguish it from the initiating step. It never names the sibling it complements (connect_account), so the differentiation is implied rather than explicit.
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 clearly states the trigger condition ('after the user approves the browser link') and gives an explicit operational constraint (do not poll faster than once per 5 seconds). It also decodes the pending state, but never names an alternative tool or states what to do if the flow fails.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.