Skip to main content
Glama

dejo_login

Opens a visible browser window so the user can sign in to a website, then preserves that login in the current browser profile.

Instructions

Sign in to a website, website login, SSO, Google sign-in, one-time code. Opens a visible browser window so the USER signs in; never type a password you were not given. Call with site, tell the user to sign in there, then call again with done=true. Signs in the current profile only, and it stays signed in.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "site": "<site>"
    },
    "name": "dejo_login"
  }
}

Input Schema

NameRequiredDescriptionDefault
doneNothe user says they are signed in
siteYes
confirmedNouser insists, though a sign-in page still shows

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.0

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses that a visible browser window opens, that the USER performs the authentication, that credentials must not be fabricated, and that the session persists for the current profile. It does not describe failure behavior (e.g., what happens if sign-in is never completed) or rate/latency characteristics, which keeps it short of a 5.

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?

Front-loads the action, then the trigger keywords, then the procedure and constraints. The lead phrase reads partly as keyword stuffing for retrieval, but every subsequent clause (visible window, no invented passwords, done loop, profile scope) carries operational weight.

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?

For a 3-parameter tool with no annotations and no output schema, the description supplies the authentication model, the interaction loop, and the safety rule. What remains thin is the outcome side: no statement of what a call returns or how an incomplete sign-in is surfaced, and 'confirmed' is never contextualized.

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

Parameters4/5

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

Schema coverage is 67%, with site undocumented in the schema; the description compensates by framing site as the target for the flow. More importantly, it explains the two-phase meaning of done=true beyond the schema's terse gloss, though 'confirmed' (user insists despite a sign-in page) is left entirely to the schema.

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

Purpose5/5

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

States a specific verb and resource ('Sign in to a website') and immediately enumerates the concrete flows it covers: SSO, Google sign-in, one-time code. An agent can tell exactly which class of task routes here, and none of the siblings (manage, memory, profile, run) is a plausible substitute.

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?

Gives an explicit two-call protocol: call with site, instruct the user to sign in, then call again with done=true. It also states a hard constraint ('never type a password you were not given') and a scoping exclusion (current profile only), so the agent knows both the sequence and the boundary of what it may do.

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