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?
Annotations only provide idempotent and non-destructive hints. The description adds valuable behavioral context: the permanent non-expiring config approach vs session-only login, the link-generation behavior with no args, and the header format. It does not disclose what happens on invalid tokens or whether server state changes, but the added context is solid.
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?
Two sentences with a clear 'Best' vs 'Or' structure, and every clause earns its place. Slightly verbose in the first sentence, but the front-loaded purpose and scannable alternatives make it effective.
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?
The description covers the main flows and return for the no-args case (get the link), but does not describe the return value when a token is passed, nor any failure modes. With no output schema and no additional annotations beyond idempotency, this is a noticeable gap for an authentication tool.
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 has a single token parameter with no description, but the description fully explains it: it is an optional JWT pasted by the user for session-only login, and omitting it returns the login link. This completely compensates for the schema's lack of detail.
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 states the tool's purpose: authenticating the user for this MCP server by logging in the browser and obtaining an access token. It distinguishes itself from the sibling calculo_* tools, which are calculation-oriented, though it does not explicitly name an alternative auth tool.
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 description provides explicit guidance on when to use each invocation mode: permanent setup via config header vs session-only login by pasting a token, and using no args to get the login link. It lacks an explicit 'do not use when already authenticated' note, but the conditional routing is clear.
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 calculo_* tools are largely distinct by legal scenario, but several overlap in mechanics—calculo_atualizar, calculo_pensao, calculo_restituicao_inss, and calculo_rmc_rcc all apply correction and interest to overdue amounts. Platform tools also blur boundaries: authenticate/connect both deal with credentials, and marketplace/toolkit_info both describe installation state.
The 16 calculation tools consistently follow a calculo_<domain> snake_case pattern, which is good. However, the 6 platform tools break the convention with single verbs/nouns (connect, marketplace, authenticate) and mixed forms (report_bug, show_version, toolkit_info), creating two inconsistent naming styles within one server.
22 tools is at the high end of reasonable for a legal-calculation suite, but the server name 'Cálculo de FGTS' suggests a much narrower scope. The platform-management tools add bulk and make the set feel broader and heavier than the name implies.
As a Brazilian legal calculation toolkit, the coverage is strong: labor, pension, criminal sentencing, family, banking, FGTS, and monetary correction are all represented. Minor gaps exist—such as no OCR extraction for FGTS statements and no standalone interest-only calculation—but the core calculation workflows are not dead-ended.