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 discloses key behaviors: the token can be set permanently via config or temporarily via parameter. It correctly indicates idempotency (idempotentHint=true) and does not contradict annotations. However, it does not mention potential failure modes or what happens on invalid tokens.
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 includes context ('MCP.AI for IDE agents') that is slightly extraneous and could be more concise. The core instructions are clear, but the first sentence could be trimmed without losing meaning.
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 a single optional parameter and no output schema, the description covers the main use cases (session and persistent login) adequately. It lacks details on error handling or token validation, but overall completeness is good for a simple authentication tool.
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 0% description coverage, but the description fully explains the 'token' parameter: it is a JWT obtained by the user, and calling without it returns a link. This adds critical meaning beyond the schema, compensating for the lack of schema descriptions.
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 function: authentication via browser login and token retrieval. It specifies exactly what the tool does (returns a link or accepts a token) and distinguishes between two usage modes, making the purpose unambiguous.
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 provides explicit guidance on when to use each method: best to add the token to config for permanent access, or paste it for session-only. It also explains calling with no args to get the link. However, it does not explicitly compare to sibling tools or state when not to use this tool.
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.
The core Omie operations are distinct by resource and action, and the descriptions actively call out edge cases like omie_lancar vs omie_create_payable/receivable and transfer vs manual entries. A few pairs (list_payables/list_receivables/list_financial_movements/list_checking_account_entries) still overlap enough that an agent could pick the wrong one on first attempt.
The dominant pattern is clear and consistent: omie_verb_noun with create, get, list, update, delete, settle, cancel, and reconcile. The main deviations are the Portuguese helper omie_lancar and the unprefixed platform-level tools like authenticate, connect, marketplace, and toolkit_info, which break the otherwise regular naming scheme.
With 50 tools, this server is far beyond the 3-15 well-scoped range and sits at the extreme end of the rubric. Most of the tools are individually purposeful, but exposing checkings, payables, receivables, reconciliation, attachments, invoicing, batch upserts, and an entire marketplace platform in one server heavily taxes an agent's tool-selection space.
The core financial lifecycle is well covered: create, read, update, delete, settle, cancel, reconcile, unreconcile, transfer, attachment upload, and batch upsert. Minor gaps exist—invoices are list-only, customers have no delete operation, and there is no dedicated get-by-id for checking accounts—but these are workable for the main reconciliation workflows.