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?
Beyond annotations (idempotent=True, destructive=False), the description adds behavioral nuance: it explains the permanence difference between header config (non-expiring) and session-only token, and that calling with no args returns a link for browser login. However, it does not disclose the exact response format for either call, leaving some ambiguity for the agent.
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 relatively compact but packed with necessary information. The opening 'MCP.AI for IDE agents' sets context, though it could be trimmed. Each sentence adds functional value, and the flow (no args -> link, token -> session) is clearly front-loaded.
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 covers the core workflow and two authentication paths. The main gap is lack of explicit return-value specification, but the phrase 'get the link' and the overall context make it reasonably complete for an agent to handle the interaction.
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?
With schema description coverage at 0%, the description fully compensates by explaining the 'token' parameter as a JWT to paste, and the meaning of omitting it (get a link). This gives the agent complete understanding of the only parameter's role.
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: authenticate for IDE agents by logging in via browser and obtaining an access token. It distinguishes between two auth modes (permanent config header vs session-only token), making the verb+resource specific. The sibling 'connect' likely differs, but the description sufficiently explains the scope.
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?
Explicit usage instructions are provided: 'Best: add it to this server's config as a header...' for permanent access, 'Or paste it here for a session-only login,' and 'call with { token: ... }' vs 'with no args to get the link.' This clearly tells the agent when to use each invocation pattern, including a step-by-step flow ('after the user pastes').
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.
Each tool has a clearly distinct function: authentication, the specific Bolsa Família query, connection status, marketplace operations, bug reporting, version display, and toolkit info. There is slight overlap between `connect` and `toolkit_info` regarding connection status, but descriptions clarify their different scopes.
Tool names mix languages and conventions: English verbs (`authenticate`, `connect`), snake_case Portuguese (`bolsa_familia_consultar`), single-word nouns (`marketplace`), and verb_noun in English (`report_bug`, `show_version`). This inconsistency makes the naming pattern unpredictable.
Seven tools is a reasonable number, but the scope is muddled: six tools are generic MCP.AI platform operations while only one is specific to the 'Bolsa Família' domain. This mismatch makes the count feel bloated for the apparent purpose of a benefits query server.
If the domain is Bolsa Família, the surface is severely incomplete (only a single consult operation, no eligibility or benefit details). If the domain is the mcp.ai platform, it is fairly complete (auth, marketplace, toolkit, feedback, version), but the server name suggests otherwise. Notable gaps exist under either interpretation.