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?
The description adds useful context beyond annotations: no-args calls return a link, token calls authenticate a session, and config-header auth is permanent/non-expiring. Annotations already provide idempotent=true and destructive=false, so the description's extra flow information is valuable. It does not cover failure/error behavior, which keeps it short of a 5.
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 compact and front-loaded with purpose, followed by two useful usage paths. There is no filler, but minor phrasing like 'log in in the browser' and the informal 'Best:' construction prevent a perfect structure score.
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 tool with strong annotations, the description covers the key flows: permanent header-based auth, session-only token auth, and no-args link retrieval. Since there is no output schema, it could say what happens after token submission, but the core use cases are sufficiently explained.
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 one token string with 0% description coverage, so the description must compensate. It does: the token is a JWT pasted by the user, it is optional, and omitting it triggers link retrieval. This is solid for a single optional parameter, though it could explicitly state that token absence is valid.
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 identifies this as an MCP.AI authentication tool: 'log in in the browser, copy the access token' and then use it for a session or permanent connection. It is specific enough to be usable, but it does not explicitly distinguish itself from the sibling 'connect' tool.
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 gives practical when-to-use guidance: prefer adding the token as a server config header for a permanent connection, or paste it for a session-only login. It also explains call modes ('call with { token }' vs 'no args to get the link'), though it does not name alternative tools or state explicit when-not-to-use conditions.
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 core tribunal tool is distinct, but several platform tools overlap: marketplace also covers connection status, installs, billing, and bug reporting, blurring boundaries with connect, toolkit_info, and report_bug. authenticate and connect also have overlapping auth/connection responsibilities, so an agent could easily pick the wrong tool.
Names are readable and mostly lowercase/underscore style, but the pattern is mixed: single verbs like authenticate/connect, noun-only marketplace, verb_noun like report_bug/show_version, noun_noun like toolkit_info, and a long Portuguese domain-specific name. There is no fully consistent convention across the set.
Seven tools is a reasonable raw count, but six of them are generic MCP platform management tools while only one serves the server's stated Tribunal TRT4 purpose. This is an inappropriate scope: the platform tooling crowds out the actual domain functionality.
The tribunal domain surface is essentially one consult operation, which may cover a simple single-lookup workflow but offers no variants for different search inputs or result navigation. The platform meta-tools add breadth, but they do not fill domain-specific gaps; if the intended use case is broader than a single consultation, the surface is thin.