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 already indicate idempotentHint=true and destructiveHint=false, and the description adds meaningful behavioral context: it discloses that calling with no arguments returns a link, that pasting a token enables a session-only login, and that configuring a header creates a permanent non-expiring connection. This goes beyond what annotations state, though it does not describe error cases or the exact response format.
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 three sentences, dense but not overly long. Every sentence adds value: the first introduces the tool, the second explains the permanent config method, and the third explains the session-based alternative. It is slightly verbose but well-structured and 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 simple auth tool with one optional param and no output schema, the description covers the essential workflows: permanent config header and session token. It also hints at the return behavior (getting a link). It lacks details about error conditions or what the response object looks like, but given the tool's simplicity, it is reasonably complete.
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 0% schema description coverage, the description fully compensates by explaining the 'token' parameter: it is optional, a JWT, used for session-only login, and omitting it returns a link. This is significant meaning beyond the schema's bare property definition.
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: to authenticate an IDE agent by obtaining an access token, either through a browser login or pasting a JWT. It specifies the resource (MCP.AI access token) and provides distinct usage paths, which makes it specific. However, it does not explicitly differentiate itself from sibling tools like 'connect' or 'marketplace', so it misses the full marks for sibling differentiation.
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 when-to-use guidance: it instructs the agent to add the token to the server config for a permanent connection or paste it for a session-only login. It explains the trade-offs (permanent vs. session-only). However, it does not explicitly state when not to use this tool or name alternative sibling tools, so it stops short of a 5.
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.
Tools like authenticate, connect, marketplace, report_bug, show_version, toolkit_info, and tribunal_trt19_processo_consultar each have distinct purposes and clear descriptionsabile. While marketplace and toolkit_info overlap slightly in scope (both relate to installed MCPs), they are not easily confused. The one domain-specific tool is clearly separate from the platform utilities.
Naming is inconsistent: six tools use short English verbs (authenticate, connect, report_bug, etc.), while the domain tool uses a long Portuguese snake_case name (tribunal_trt19_processo_consultar). This mix of languages and naming conventions creates a jarring and unpredictable pattern.
At 7 tools, the raw count falls in a reasonable range, but the composition is mismatched with the server's stated purpose of 'Tribunal TRT19: Consulta Processual'. Six out of seven tools are generic platform utilities unrelated to the domain, leaving only one actual domain tool. The count is not appropriate for the declared scope.
The server's purpose appears to be querying TRT19 process data, but only one tool (tribunal_trt19_processo_consultar) serves that purpose, with no additional operations like search, list, or details. The rest of the tools relate to MCP platform management, which does not contribute to the domain surface. Obvious gaps exist for even basic workflow support.