Finalize LinkedIn OAuth sign-in by waiting for loopback callback or exchanging a redirect URL, then saving the session locally.
Finish member sign-in. Waits for the loopback callback, or exchanges a pasted redirect URL. Saves the session locally.
| Name | Required | Description | Default |
|---|---|---|---|
| redirectUrl | No | Full redirect URL if the callback was not received on loopback. | |
| timeoutSeconds | No | How long to wait for the callback. Defaults to 120. |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does disclose meaningful behavior: it completes an auth handshake and persists a session locally, a real side effect an agent should know about. It stops short of describing failure/timeout outcomes or what the saved session grants, leaving some gaps for a mutation-bearing auth tool.
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, front-loaded with the core action, then the two operating modes, then the side effect. No filler; every clause contributes.
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 an auth-completion tool with no output schema and no annotations, the description covers the essential flow and side effect. It could be more complete by stating ordering relative to linkedin_login or what happens when the callback is never received (beyond the timeout default living in the schema), but nothing critical is missing.
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%, so both parameters (redirectUrl, timeoutSeconds) are already documented with ranges and defaults. The description references 'pasted redirect URL' and the wait behavior but adds no syntax or format detail beyond the schema, so 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 ('Finish member sign-in') and clarifies the mechanism, making it distinguishable from the sibling linkedin_login that presumably starts the flow. The word 'Finish' implies it is the continuation step, but the description never explicitly names linkedin_login, so the sibling relationship is only inferred.
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 two modes ('waits for the loopback callback, or exchanges a pasted redirect URL') implicitly tell the agent which input path to take, but there is no explicit 'use after linkedin_login' or when-not guidance and no mention of alternatives like linkedin_status for checking auth state.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.