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 idempotentHint=true and destructiveHint=false. Description adds that calling with no args returns a link, and with token it logs in. It does not contradict 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?
Description is clear and front-loaded, but slightly verbose. Could be trimmed while retaining all key information. Still, every sentence adds value.
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?
Covers both use cases and required steps. With no output schema, missing return value details, but for authentication the side effect (logged in state) is the main outcome, which is implied.
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?
Only parameter 'token' has 0% schema coverage but the description fully explains its purpose: paste the JWT for session login. Also clarifies the alternative of using config for permanent token.
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 is for authentication, explaining how to log in via browser or paste token. It distinguishes two methods: permanent config or session-only login with token parameter. No ambiguity.
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?
Explicitly explains when to use each approach (permanent vs session), and provides alternative (config header). Also mentions that calling with no args returns a link for initial login.
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 distinct, especially the f360_* family which separates listing, detail, and report generation per resource. However, 'authenticate' and 'connect' both deal with connection state, and 'f360_list_accounts' vs 'f360_listar_planos_contas' could be confused without reading descriptions closely.
Naming is inconsistent: generic tools use simple English verbs (connect, show_version), while financial tools mix English (list_accounts) and Portuguese (listar_notas, obter_xml) with inconsistent verb forms and prefixes. The patterns are not predictable across the full set.
At 19 tools, the set is borderline heavy. Six tools (authenticate, connect, marketplace, report_bug, show_version, toolkit_info) are platform-level utilities unrelated to the financial domain, inflating the count; the remaining 13 financial tools are well-scoped for a read-only reporting API.
The financial tools cover listing and detail retrieval for core entities (accounts, notes, people, chart of accounts) and generate/download reports. However, there are no create/update/delete operations, and no getter for accounts or other entities, limiting the surface to read-only reporting.