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 the tool non-read-only, idempotent, and non-destructive. The description adds useful behavioral details: with no args the tool returns a link, with a token it performs a session-only login, and the config-header method gives a permanent non-expiring connection. It does not mention error cases or what happens on repeated token submissions, but the core behavior is disclosed.
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 compact and front-loads the purpose before explaining the two authentication paths. The flow is a bit run-on and could be broken into bullets, but every sentence contributes useful information.
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 tool with one optional parameter and no output schema, the description is largely complete: it covers the user flow, token passing, link retrieval, and permanent versus session-only behavior. It does not specify the exact return value for the token-call success case, which is a minor gap.
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?
Schema coverage is 0%, so the description must carry the meaning. It does so by showing the exact invocation `{ token: "<jwt>" }` and explaining that calling with no args returns the link. This clearly conveys that the token parameter is optional and what it represents.
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 communicates that this tool handles authentication: it provides a login link when called with no arguments and accepts an access token for session-only login. It goes beyond the title 'Authenticate' by describing the actual login flow, though it does not name any sibling tools to distinguish itself.
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 explicitly recommends the permanent config-header approach as the best alternative, and states that pasting a token here is for session-only login. It also gives the no-args invocation as the way to obtain the link, providing clear when-to-call guidance.
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 stone_vendas_* tools are clearly separated by data type, but the generic tools are not: connect, toolkit_info, and marketplace all describe connection/installed-tool state, and marketplace even mentions report_bug functionality that is also a standalone tool. Agents could easily pick the wrong meta-tool when checking status or running another MCP.
The Stone tools share a consistent stone_vendas_ prefix, but the rest of the server uses bare English verbs/nouns like authenticate, connect, marketplace, and toolkit_info. Inside the prefix, the names mix verbs like listar and limpar_cache with nouns like arquivo, recebiveis, and resumo, so no single naming pattern governs the set.
15 tools is not extreme, and the nine Stone-specific tools are reasonably scoped. However, six generic MCP.AI/admin tools are unrelated to Stone Vendas and dilute the server's purpose, making the count feel padded.
The Stone domain covers the main reconciliation workflow well: sales, Pix, settlements, receivables, cancellations/chargebacks, account listing, a catch-all daily file, and cache reset. There are minor gaps like a direct single-transaction lookup or an explicit bank-statement reconciliation tool, but core reporting has no dead ends.