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 the annotations (idempotent, non-destructive, not read-only), the description discloses key behaviors: calling with no args returns a link, passing a token establishes a session-only login, and configuring the header gives a permanent non-expiring connection. It explains the difference between session and permanent authentication, adding useful context on how the tool behaves.
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 slightly verbose but well-structured, with each sentence contributing necessary information. It front-loads the context (MCP.AI for IDE agents) and then guides through configuration options. It could be tightened but is efficient and not redundant.
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 no output schema, the description covers all usage modes: permanent configuration via header, session login via token, and retrieval of the login link. It is complete enough for an agent to invoke correctly in various scenarios.
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 only defines token as a string with no description. The description fully compensates by explaining that token is a JWT obtained from the browser, it is optional (can call with no args to get a link), and it is used for session-only login. This adds rich 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 clearly states the tool's purpose: authenticating MCP.AI for IDE agents by logging in via browser and retrieving an access token. The verb "authenticate" is specific to the login action and is distinguished from siblings like "connect" by focusing on token-based authentication. The resource (MCP.AI access token) is explicitly mentioned.
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 provides clear usage scenarios: for a permanent connection, add the token as an Authorization header in config; for a session-only login, call with the token; for getting the login link, call with no args. It implicitly contrasts the permanent vs. session approaches but does not explicitly reference sibling tools like "connect" as alternatives. This is clear context without explicit exclusions.
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 tribunal lookup tool is clearly distinct, and most platform tools have individual roles. However, marketplace is a broad multifunction tool that includes its own report_bug, connect, list_tools, and invoke behaviors, and connect/toolkit_info both report connection status, so an agent may need to read carefully to avoid picking the wrong entry point.
Names like report_bug, show_version, and toolkit_info are clear snake_case, but the set mixes bare verbs (authenticate, connect), bare nouns (marketplace), and a long Portuguese domain name (tribunal_trt5_processo_consultar) that reverses the usual verb_noun order. The style is readable but not consistently patterned.
Seven tools is a reasonable count overall, but only one tool actually addresses the named Tribunal TRT5 purpose. The other six are generic platform and toolkit-management tools, so the toolset feels padded for a server that presents itself as a Brazilian court-case consultation service.
The single tribunal tool likely supports a basic case consultation, but the domain surface is thin: there is no clear support for different consultation modes, expanded case detail endpoints, or follow-up actions such as downloading or saving process information. Minor context writing around the main query could be enough for read-only use, but the missing tool shapes are notable.