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 (idempotentHint true, destructiveHint false) already cover safety. The description adds context about permanent vs. session-only behavior and that calling with no args returns a link, but doesn't detail error handling or token validation. This adds value beyond annotations, though a bit more nuance could be given.
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 two sentences, front-loaded with context, and every sentence adds actionable information. It efficiently packs both authentication modes and the exact call signature without verbosity.
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 authentication tool with one optional parameter, the description covers all usage scenarios: permanent vs. session, how to obtain a link, and expected input format. It is complete enough for an agent to decide and invoke correctly.
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% coverage for the token parameter, but the description fully explains it: token accepts a JWT when pasted, and omitting it returns a link. This completely compensates for the missing schema documentation.
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 authenticates the MCP.AI server for IDE agents, with specific verb+resource and distinct methods (config header vs. token). It effectively differentiates from siblings like 'connect' by detailing the authentication flow.
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 describes when to use each approach: permanent via config header, session-only via token, and how to initiate (with or without token). It also instructs to call with no args to get a link, providing clear contextual usage.
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 tools include a mix of platform management functions (authenticate, connect, marketplace, report_bug, show_version, toolkit_info) and one domain-specific tool (tribunal_trt2_processo_consultar). While the platform tools are distinct, the 'marketplace' tool has a very broad and complex description that overlaps with 'toolkit_info' and 'connect' in terms of installation and connection status; also 'report_bug' is narrow and could be considered an action within a platform, but not clearly distinct from feedback features of other tools.
Most tools use a simple lowercase verb or noun (authenticate, connect, marketplace, report_bug, show_version, toolkit_info), which is somewhat consistent but lacks a clear verb_noun pattern. The domain-specific tool 'tribunal_trt2_processo_consultar' follows a completely different naming convention (domain prefix + process + verb), breaking the pattern. The verbs are also vague (authenticate, connect) and mixing verbs and nouns.
The server has 7 tools, which is within a reasonable range. However, the tool set is very top-heavy on platform management and only has one actual domain-specific tool for the legal process consultation. For a server named 'Tribunal TRT2: Consulta Processual', the user would expect more tools related to the legal domain; the current count feels slightly over-scoped with platform tools and under-scoped for the domain.
The domain is likely about querying Brazilian labor court procesos (TRT2). However, the only domain tool is a single 'consultar' action, which is a read-only query. There are no tools for listing, filtering, updating, or managing anything related to procesos. The rest of the tools are for the MCP platform itself, not the legal domain, so the tool surface is severely incomplete for the stated purpose.