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?
Annotations already indicate idempotentHint=true and destructiveHint=false. The description adds valuable context about the two login modes (permanent vs session-only) and how the token is handled, which goes beyond the annotations. No contradictions detected.
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, somewhat dense sentence but remains readable. It front-loads the purpose and then provides examples. Slightly verbose with the 'MCP.AI for IDE agents' prefix, but every clause contributes to understanding.
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 authentication tool with one optional parameter and no output schema, the description covers the core use cases and behavior. It does not mention return values or error handling, but that is minor given the simplicity and existing annotations.
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?
Schema has only 'token' with no description (0% coverage). The description fully compensates by explaining the token is a JWT for session-only login and that calling without it returns a link. This gives clear meaning to the parameter and its optionality.
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 users via a browser login and token retrieval. It specifies the action ('log in', 'copy the access token') and distinguishes it from sibling tools implicitly by focusing on authentication flow. It is specific and not a tautology.
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?
Provides clear usage instructions: two methods (permanent via config header, or session-only via token argument) and explains the no-argument behavior. It does not explicitly contrast with sibling tools like 'connect', but the context is clear enough for the agent to know when to call it (initially or when token expires).
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 tool has a clear primary purpose: authentication, data consultation, connection status, marketplace discovery, bug reporting, version info, and toolkit state. The only slight overlap is between connect (connection status) and toolkit_info (connection status plus installed MCPs), which could cause minor misselection but is mitigated by detailed descriptions.
Naming is inconsistent: some tools use a verb (authenticate, connect), some use noun phrases (marketplace, toolkit_info), and the domain tool car_download_shapefile_consultar mixes a long domain prefix with an action suffix. There is no uniform convention, making it harder to predict tool names.
Seven tools exist, but only one (car_download_shapefile_consultar) actually serves the server's stated purpose of downloading CAR shapefiles. The remaining six are generic platform utilities, leaving the domain-specific functionality extremely thin for the apparent scope.
The single domain tool appears to handle the core query/download operation, but there are no supporting tools for listing available datasets, filtering by region, or validating inputs, which would be expected for a shapefile download service. Agents will likely need to rely on the marketplace tool to fill gaps, indicating an incomplete surface.