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 behavior. The description adds context about session-only vs permanent connection, and that no args returns a link. No contradictions with annotations.
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 front-loaded with the core purpose. The IDE agent preamble adds context but could be trimmed. Overall, every sentence serves a purpose.
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 auth tool with an optional token and no output schema, the description covers the essential flows: pasting a token, getting a link, and configuring a permanent header. It doesn't detail the response shape but says 'get the link', which is sufficient.
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 only lists a token string with no description. The description explains the token is a JWT pasted by the user, and that omitting it triggers a login link. This fully 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 authenticates the MCP.AI server for IDE agents, with specific actions: pasting a JWT token for session login or getting a browser link. It explicitly differentiates itself from siblings by focusing on authentication.
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 explicit usage scenarios: permanent connection via config header, session-only via token, or no args to obtain a link. The 'Best' recommendation adds practical guidance, though it doesn't explicitly exclude other 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.
Each tool has a clearly distinct purpose: authenticate handles login, connect reports connection status, marketplace manages MCP discovery/execution, report_bug sends feedback, show_version displays version, toolkit_info shows installed state, and the last performs the actual transparency query. No two tools overlap in function.
Naming is inconsistent: English platform tools use short verbs/nouns (authenticate, connect, marketplace, report_bug, show_version, toolkit_info), while the sole domain tool is a long Portuguese phrase (transparencia_indicadores_pj_consultar). The verb is at the end and the language differs, breaking any predictable pattern.
Seven tools is within a typical range, but the count is skewed: six are generic platform utilities and only one serves the server's stated purpose (PJ indicators). The composition feels unbalanced, though not extreme in either direction.
The domain surface is minimal—only a single consult operation for CNPJ indicators. There are no discovery or metadata tools (e.g., listing available indicators or describing fields), which limits agent flexibility. The platform tools cover their own lifecycle, but the transparency domain itself lacks depth.