MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header Authorization: Bearer <token> for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "" } after the user pastes, or with no args to get the link.
| Name | Required | Description | Default |
|---|---|---|---|
| token | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the sparse annotations (idempotent only), the description reveals the browser-based flow, permanent vs session-only login behavior, and the no-args link generation. It doesn't disclose what a successful token call returns or error/failure behavior, but the provided behavioral context is meaningful.
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 brief sentences front-load the purpose and then pack the necessary configuration and invocation details. Every clause adds actionable information, and the inline code formatting improves scanability.
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 a simple one-parameter auth tool, the description covers the two invocation modes and how to obtain a token, which is sufficient for an agent to invoke it. It lacks explicit return/error semantics and has no output schema, leaving a small completeness gap.
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 schema only lists an optional `token` string with zero description coverage, so the description carries the entire semantic burden. It defines `token` as a JWT for session-only login and explains the no-args case, fully compensating for the schema's silence.
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 identifies this as the MCP.AI authentication tool for IDE agents and gives concrete actions: browser login, token capture, and optional token submission. This sets it apart from sibling utilities like connect/report_bug and makes the tool's function unmistakable.
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 explicitly contrasts the recommended permanent header configuration with the session-only token call, and states exactly when to pass a token versus call with no arguments to get a link. It doesn't name sibling alternatives or explicit when-not conditions, so it stops short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The only clearly domain-specific tool is tribunal_trt6_processo_consultar; the rest are overlapping platform/admin tools. marketplace internally duplicates report_bug, status, install, and invocation capabilities that also exist in authenticate, connect, toolkit_info, and report_bug, so an agent can easily pick the wrong meta-tool.
Naming follows no clear pattern: one-word name/verb patterns, simple verb_noun forms like report_bug and show_version, and a long snake_case Portuguese name like tribunal_trt6_processo_consultar. There is no predictable naming convention across the tool set.
Seven tools is not an excessive count by itself, but most of them are general-purpose platform controls rather than tribunal-domain capabilities. The marketplace tool also acts as an umbrella for many sub-operations, making the actual complexity higher than the tool count suggests.
For a tribunal consultation server, only one tool actually provides domain data, so the agent can perform a basic lookup but has no additional court-domain operations such as searching, filtering, or interpreting multiple processes. The rest of the tools are platform infrastructure and do not complete the legal domain workflow.