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 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (idempotentHint true), the description adds behavioral details: it explains the two authentication methods, the fact that config is permanent and token is for session, and the link retrieval. No contradictions.
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 a single paragraph, but well-structured and front-loaded with audience context. Every sentence adds value, covering different scenarios without redundancy.
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?
Given no output schema and simple annotations, the description covers all necessary aspects: the authentication flow, two methods, and instructions for the agent. It is sufficiently complete for the tool's purpose.
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 input schema has one parameter 'token' with no description. The description fully explains its meaning (a JWT), how to obtain it (via browser login), and how to use it (paste and call with token or no args for link). This compensates for the 0% schema coverage.
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: to authenticate for IDE agents like Cursor. It specifies the action ('log in') and the resource (the MCP server), and distinguishes itself from sibling tools which are functional (e.g., ifood, toolkit).
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 two usage scenarios: permanent config setup (adding Authorization header) and session login (pasting token). It also explains that calling with no args returns a link, giving clear context for use.
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.
Each iFood-specific tool targets a distinct resource (catalog, availability, financial summary, store, order detail, order list, transactions). The generic platform tools (authenticate, connect, marketplace, etc.) are also distinct. The only slight overlap is between connect and authenticate, but their descriptions clearly separate connection status from token-based login.
Names are all snake_case but follow mixed patterns. The iFood tools use a consistent 'ifood_vendas_' prefix followed by nouns or noun phrases (cardapio, disponibilidade, financeiro_resumo, pedido_detalhe). Platform tools use imperative verbs (authenticate, connect, report_bug) or descriptive names (toolkit_info). No uniform verb_noun convention exists across the set.
13 tools is within a reasonable range, but 6 of them (authenticate, connect, marketplace, report_bug, show_version, toolkit_info) are generic platform utilities unrelated to iFood. This makes the server feel like a mixed bag rather than a focused iFood integration, reducing appropriateness for the server's stated purpose.
The iFood tools cover read-only workflows: catalog, availability, financial summary, store data, order listing, order detail, and financial transactions. However, there are no write operations (e.g., update menu, cancel order) and no search/filter capabilities beyond basic period-based listing. Core read operations are covered, but the surface is incomplete for full lifecycle management.