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 indicate readOnly=false, destructive=false, and idempotent=true. The description adds useful behavioral context beyond annotations: browser-based login, permanent header vs session-only token, and no-args behavior returning a link. No contradiction with annotations is present.
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 moderately sized and structured with 'Best:' and 'Or' to separate options. All included information is relevant to using the tool correctly, though the single long sentence is slightly dense.
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 the simple optional-parameter schema and no output schema, the description covers the main invocation modes and the overall auth workflow. A minor gap is that it does not state what happens after submitting a token, but this is not essential for correct invocation.
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 optional 'token' parameter with 0% description coverage. The tool description compensates well by explaining that the token should be a JWT for session-only login and that omitting the token returns the login link.
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 indicates this tool handles authentication for MCP.AI IDE agents, explaining the browser login flow and access token usage. It is specific about the action ('log in', 'copy the access token') but does not explicitly distinguish itself from the sibling tool 'connect'.
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 provides clear usage guidance: use the config header for a permanent non-expiring connection, or call the tool with a pasted JWT for session-only login, or call with no args to get the login link. However, it does not explicitly state when not to use this tool or mention alternative sibling tools.
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.
Tools have clearly distinct purposes: authentication, connection status, a single CPFL query, marketplace management, bug reporting, version info, and toolkit info. No two tools seem to overlap in function, though `connect` and `toolkit_info` both touch connection status but are still differentiated by scope.
Naming is inconsistent: English verbs (authenticate, connect, report_bug) mixed with Portuguese camelCase (`contas_cpfl_link_ocr_consultar`), and a mix of snake_case (`report_bug`, `show_version`, `toolkit_info`) and lowercase single words (`marketplace`). No uniform pattern.
Seven tools is within the typical well-scoped range derived from the calibration. However, most tools (6 of 7) are generic platform utilities rather than domain-specific to CPFL, so the count feels padded for the server's stated purpose but is not excessive.
The server claims to be 'CPFL: Download via link + OCR' but only offers a single domain-specific operation (`contas_cpfl_link_ocr_consultar`). Missing are common operations like listing multiple accounts, downloading bill documents, or managing OCR tasks. The rest are platform utilities that do not address the domain, leaving significant gaps for an agent trying to accomplish CPFL-related tasks.