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 meaningful behavioral context beyond the annotations: the no-arg link flow, the session-only nature of passing a token, and the non-expiring behavior of the config header. It does not contradict the readOnly, destructive, or idempotent hints, but it does not cover expiration or failure behavior.
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 reasonably compact and front-loaded with the core auth flow. It contains a slightly awkward introductory phrase and some redundancy, but every sentence contributes useful operational detail.
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 an authentication tool with no output schema and one optional parameter, the description explains the login link mode, session token mode, and a permanent alternative. It does not mention expiration, error cases, or returned status payloads, but these are not required by the exposed schema and 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?
Despite having 0% schema description coverage, the description fully documents the optional token parameter: it identifies the JWT format, shows the exact invocation shape, and explains that omitting the token yields a login link. This more than compensates for the bare schema.
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?
Clearly shows this is the authentication entry point for the MCP server, with a browser-login flow and a token-paste flow. It is much more specific than the tool name alone, though it does not explicitly contrast itself with the sibling 'connect' tool.
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 gives concretely actionable guidance: call with no arguments to receive a link, call with a pasted JWT for session-only login, and add the token as a header in the server config for a permanent connection. It also highlights the recommended option without being ambiguous.
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 clearly separated by resource and action (e.g., clientes_create vs. produtos_create), and the CRUD verbs are distinct. However, a few non-CRUD actions like cancelar_create and emitir_create carry a misleading '_create' suffix, and the connection tools (connect, list_accounts, toolkit_info) have overlapping concerns.
The dominant pattern is gestaoclick_{resource}_{verb}, which is predictable for the large CRUD set. But exceptions like gerar_parcelas_create, cancelar_create, and emitir_create append '_create' to non-creation actions, and standalone tools (authenticate, connect, marketplace, report_bug, show_version) do not follow the resource-based convention at all.
133 tools is far beyond the 'too many' threshold and will heavily burden an agent's tool-selection process. While the set may reflect a large ERP API, the sheer volume makes the server unwieldy and poorly scoped for typical agent use.
Core entities (clientes, produtos, vendas, compras, orcamentos, ordens_servicos, notas fiscais, etc.) have full CRUD plus important domain actions like emitir, cancelar, and gerar_parcelas. Minor gaps exist: many reference/lookup entities are list-only, and some lifecycle actions for those reference tables are missing, but overall the main workflows are covered.