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 already declare idempotent and non-destructive, but the description adds valuable behavioral detail: the permanent config route vs session-only token, and that calling with no args returns a link. It does not contradict annotations and clarifies side effects (session vs permanent) beyond what annotations convey.
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?
The description is compact at three sentences, each carrying a distinct purpose: the flow, the permanent config option, and the session option. It uses inline code formatting for clarity without waste.
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 one-parameter auth tool, it covers all main usage modes, the token type, and the no-arg behavior. It doesn't mention error handling or exact response format, but the return link is implied. Given no output schema and a simple tool, this is adequately complete.
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 only a bare token string with 0% description coverage. The description fully compensates by explaining that token is an access token/JWT, used in a call like { token: "<jwt>" } after the user pastes, and that no args yields the login link. This is complete for the single optional parameter.
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 authenticates MCP.AI for IDE agents (Cursor, etc.) with an explicit process: log in in the browser, copy the access token, and either configure it permanently or paste it for a session. The verb 'log in' and the specific resource 'MCP.AI' distinguish it from sibling tools like connect or marketplace.
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 gives strong usage context: 'Best: add it to this server's config as a header... for a permanent, non-expiring connection' vs 'Or paste it here for a session-only login'. It also explains when to call with no args vs with a token. However, it does not explicitly mention alternatives among sibling tools, so it's not a full 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.
Most tools have distinct roles: authentication, status, marketplace operations, version, toolkit info, bug reporting, and the single OAB lookup. However, 'marketplace' bundles many sub-actions (search, describe, invoke, install, prompts) which could be confusing, and 'connect' overlaps with 'authenticate' in terms of connection status.
Naming is inconsistent: some are bare verbs (authenticate, connect), some are noun-style (marketplace, toolkit_info), one is Portuguese with underscores (oab_advogados_consultar), and others use underscores but with different conventions (report_bug, show_version). There is no clear verb_noun pattern across the set.
Seven tools is a reasonable number for a platform server, though most of them are generic meta-tools. The count is not excessive, but the mix of domain and platform tools feels slightly awkward. Still, it is within a typical well-scoped range.
Given the server name 'OAB Cadastro de Advogados', the only domain-specific tool is a single lookup by name and registration number. There are no other OAB-related operations (e.g., listing, verifying, or detailed info). The rest are generic platform tools, making the domain coverage severely incomplete.