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 include idempotentHint=true and destructiveHint=false, and the description adds useful context: header-based auth is permanent/non-expiring while pasted token is session-only, and no-args calls return a link. No contradictions, though it doesn't detail side effects or response behavior.
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 moderately verbose but every sentence serves a purpose: introducing the target environment, recommending the permanent header approach, and describing the session-only alternative. It is front-loaded with the most critical context and avoids fluff.
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 simple tool with one optional parameter and strong annotations, the description covers authentication flow, two usage modes, and no-arg behavior. It doesn't address return values or error cases, but since there is no output schema, this is acceptable.
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 bears full responsibility. It explains the 'token' parameter as a JWT for session-only login and clarifies that omitting it yields a login link, fully compensating for the schema's lack of property 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 indicates the tool is for authenticating with MCP.AI, explaining the browser login flow and token usage. It distinguishes from sibling 'connect' by specifying the target service and method, though it doesn't explicitly state the core action in a single verb-object phrase.
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?
It explicitly provides two usage modes: permanent via header configuration and session-only via token parameter, and states that calling with no args returns a login link. This gives clear when-to-use guidance and explains the alternative approaches.
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 single domain tool (antt_transportadora_consultar) is clearly distinct from the platform utilities. However, connect and toolkit_info both report connection/status information, creating slight overlap. The other tools serve separate purposes (auth, marketplace, bug reporting, version).
Tool names are inconsistent in style: the domain tool uses a long snake_case prefix, while the platform tools use short verbs (authenticate, connect), noun phrases (marketplace, toolkit_info), or verb_noun (report_bug, show_version). No clear pattern ties them together.
With 7 tools, the count is reasonable, but the composition is unbalanced—only one tool directly serves the ANTT domain while the other six are generic platform/management tools. The set feels like a standard wrapper with a single domain functionality tacked on.
For the stated purpose of querying ANTT carrier regularity, the single consult tool covers the essential operation (by CPF, CNPJ, or RNTRC). It lacks any supplementary domain actions, but the core query is fully addressed. The platform tools fill typical admin needs, so no critical gaps for the primary use case.