Skip to main content
Glama

sign_in

Idempotent

Launches a browser login to save an Overleaf session after user approval, enabling authenticated project access without Git integration or a premium plan.

Instructions

Open a browser window on the user's computer for them to sign in to Overleaf, and save the session, as the login command does. Call it only when the user agrees. A session that already works is returned at once and nothing opens. It waits up to 40 seconds: status waiting means the user is still signing in, so call it again only after they say they have finished. After a failure, ask the user before calling it again. Needs Google Chrome, Chromium, Brave, or Microsoft Edge.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "sign_in"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Output Schema

NameRequiredDescriptionDefault
statusYes
userIdNo
baseUrlNo
warningNo
deadlineNo
projectCountNo
authenticatedNo
alreadySignedInNo
sessionExpiresAtNo
permissionsUncheckedNo
socketPresenceNoticeNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.0

TDQS

A4.4/5.0
Behavior4/5

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

Beyond the annotations, the description discloses the 40-second wait, the meaning of the 'waiting' status, and the local browser prerequisite (Chrome, Chromium, Brave, or Edge). It also notes the consent requirement and the idempotent short-circuit when a session is already valid. The main gap is that it does not say exactly what gets written or where the session is stored.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the purpose and then lays out the consent, session-reuse, wait, and retry rules compactly. The only unnecessary phrasing is the comparison 'as the login command does', which adds little. Overall the sentences earn their place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Because the tool has an output schema, the description does not need to explain return values in detail, and it still clarifies the important 'waiting' status. It covers consent, timing, prerequisites, and retry behavior, which is enough for a no-parameter sign-in flow. The only thing missing is where the saved session is stored, which is minor.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes no parameters, so the schema does not need description coverage and the description correctly adds no parameter detail. The relevant semantics are in the status values the tool reports, and those are explained ('waiting' means the user is still signing in).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource: it opens a browser window on the user's machine so they can sign in to Overleaf and then persists that session. It also clarifies the interaction with an existing valid session (returned immediately, no window opens), which sets it apart from a plain status check. It never names the adjacent auth_status tool explicitly, so sibling differentiation is implied rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit when-to-use rules are included: call only when the user agrees, do not re-call while status is waiting until the user says they are done, and ask the user before retrying after a failure. It also states that no browser window opens when a working session already exists, which tells the agent when this tool is unnecessary.

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