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, non-read-only, non-destructive), the description explains session-specific vs permanent login, that calling with no args returns a link, and that using a token creates a session. This adds meaningful behavioral context about state and token handling that isn't in the 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?
Two sentences deliver all key information without fluff. Details are front-loaded ('log in in the browser, copy the access token'), and the prose is efficient despite the parenthetical audience note. Every clause contributes actionable 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 single-parameter optional-auth tool with no output schema, the description covers user actions, token handling, session behavior, and configuration steps. It leaves no ambiguity about how an agent should invoke it, making it complete for its complexity.
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 schema has 0% description coverage for its sole optional 'token' parameter. The description fully compensates by explaining that the token is a JWT pasted by the user, how it's used in the call, and what happens if omitted. This adds essential meaning beyond the raw 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?
The description uses specific verbs and resources: 'log in in the browser, copy the access token' and clearly distinguishes this as the authentication tool for MCP.AI IDE agents. It clearly differentiates from siblings by focusing on token-based login and linking, setting it apart from generic 'connect' or 'marketplace' tools.
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?
Provides explicit usage scenarios: 'Best: add it to this server's config... Or paste it here for a session-only login' and details exactly when to call with or without arguments. It covers the primary use cases and even gives a recommended approach, though it doesn't mention alternatives from sibling tools, that's not needed here as it's an authentication flow with distinct methods.
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 only domain tool, dprf_nada_consta_multas_pagas_consultar, is clearly distinct, but connect, toolkit_info, and marketplace overlap around connection status, installed tools, and dispatch. Their lengthy descriptions force careful reading and make tool selection ambiguous.
Six tools use short English imperative verbs such as authenticate, connect, report_bug, and show_version, but the domain tool is a long Portuguese snake_case phrase ending in consultar. The set mixes languages, lengths, and verb placement with no consistent convention.
Seven tools is not a large count, but six are generic platform utilities unrelated to the named DPRF 'Nada consta' service. The actual domain surface is a single consultation tool, so the count feels padded rather than purpose-scoped.
For a simple official-source query, the single consultation tool covers the core need and no CRUD lifecycle is expected. However, the server lacks any domain-specific supporting operations such as result history, formatting, or related consultation types, while the platform tools do not address that gap.