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?
The description adds context beyond annotations by explaining that calling with no args returns a link, while passing a token enables session-only login. It also differentiates between a permanent (header config) and session-based connection. No contradiction with annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false) exists, as the described actions are idempotent and non-destructive.
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?
Three sentences efficiently cover the context, best practice, and session alternative. Each sentence serves a distinct purpose, and the message is front-loaded with the tool's target audience and core action. No unnecessary repetition or filler.
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 one-parameter tool, the description covers the primary usage modes and token semantics. However, it does not explicitly specify return values or error conditions (e.g., what happens on successful auth or invalid token), which would improve completeness given there is no output schema.
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 defines 'token' as a string with no description, so the description carries full responsibility. It does this thoroughly by explaining the token is a JWT, that it is optional, and that omitting it generates a login link. It compensates perfectly 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: authentication for IDE agents by logging in, copying a token, and either configuring it as a header or passing it for a session. It distinguishes from siblings like 'connect' by focusing specifically on the authentication workflow, not general connection setup.
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 explicit instructions on when to use each mode: 'Best: add it to this server's config as a header...' for permanent access, and 'Or paste it here for a session-only login' with the token parameter for temporary access. It does not explicitly mention alternatives or exclusions relative to sibling tools, but the guidance within the tool is clear and practical.
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 are distinct in purpose, but there is some overlap between authenticate, connect, and marketplace—especially since marketplace's invoke can return connection links. The single domain-specific tool (cnpj_cadastral_plus_consultar) is clearly separate from the platform utilities.
Naming is inconsistent: it mixes English and Portuguese, verb-only (authenticate, connect), noun-only (marketplace), and snake_case verb_noun (report_bug, show_version) with no coherent pattern. The Portuguese tool name cnpj_cadastral_plus_consultar follows a different convention entirely.
With 7 tools, the count is reasonable, but only one actually relates to the server's apparent domain (CNPJ data). The remaining six are generic platform utilities (marketplace, connect, toolkit_info, etc.) that don't belong in a specialized server and dilute its focus.
The CNPJ domain is severely underrepresented: there is only a single query tool and no other operations such as validation, list, or update. The generic platform tools do not fill these gaps, making the set incomplete for its stated purpose.