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, the description explains important behavior: permanent non-expiring vs session-only login, the need to paste a token, and the no-args behavior returning a login link. It is transparent about the core auth flow, though it does not discuss token security or what the response looks like for token-based calls.
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 dense but well-organized: it states the audience and purpose, then offers the recommended permanent method and the alternative session method, and finally the no-arg behavior. Every clause adds useful information without repetition.
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 one-parameter authenticate tool with no output schema, the description covers the essential scenarios: browser login, token paste, permanent config, and no-args link retrieval. It does not specify the response format for token submission, but the tool is simple enough that this 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?
The schema only defines an optional 'token' string with no description, but the description fully compensates by explaining exactly how to supply it as { token: '<jwt>' } or omit it to get a login link. This gives the agent complete guidance on the single parameter.
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 that this tool authenticates the MCP.AI server for IDE agents, describing the browser login and token flow. It does not explicitly contrast itself with sibling tools like 'connect', so it lacks explicit sibling differentiation but the purpose is unambiguous.
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 provides clear usage context: use the config header for a permanent connection or pass a token for a session-only login, and call with no args to get the link. It gives actionable instructions but does not mention when not to use this tool or alternatives like 'connect'.
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.
Most tools have distinct purposes and detailed descriptions, but there are ambiguous boundaries around connection/auth status (`connect` vs `toolkit_info`) and the `marketplace` tool embeds sub-acts like `report_bug` and `list_tools` that overlap with separate tools. An agent can usually disambiguate, but not from names alone.
Names mix bare verbs (`authenticate`, `connect`), a bare noun (`marketplace`), verb_noun forms (`report_bug`, `show_version`), noun_info (`toolkit_info`), and one long Portuguese domain-specific identifier (`tribunal_tjpr_processo_consultar`). The overall snake_case is readable, but the English/Portuguese and verb/noun mix is not a coherent pattern.
Seven tools is within a reasonable count range, but six are generic mcp.ai platform utilities and only one is the actual TJPR/court domain tool. The server therefore feels inflated with infrastructure while its real domain surface remains minimal.
The direct domain coverage is essentially one generic `consultar` lookup. For a public court-process query service, a read-only tool is natural, but there are no search/browse/auxiliary operations or follow-up capabilities, leaving notable gaps if the tool is meant to support broader court research.