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 include idempotentHint=true and destructiveHint=false, which the description aligns with. The description adds behavioral context: it explains what happens when called with no args (returns a link), with token (logs in), and specifies that token is a JWT. This goes beyond the annotations by describing the login flow and the token's nature, but does not contradict them.
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 a single, dense sentence that efficiently conveys multiple key points: target audience, login method, permanent vs session options, and two distinct invocation modes. It is front-loaded with the essential purpose, though it is slightly verbose, packing many ideas into one sentence without breaks.
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?
Given the tool's simplicity (single optional parameter, no output schema, no nested objects), the description is quite complete: it covers the token format, the two modes (with/without token), and the permanent configuration alternative. However, it does not specify the output format or error handling, but with no output schema and a simple auth flow, this is acceptable.
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 description explains the only parameter (token) in detail: it should be a JWT pasted by the userebreak, and provides usage examples ('call with { token: "<jwt>" }'). With schema coverage at 0%, the description compensates by fully explaining the parameter's purpose and format, earning a high score despite the sparse 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: to log in to the IDE via browser and obtain an access token. It specifies the action (authenticate), the resource (this server's config), and distinguishes from siblings by being the unique authentication tool among the listed siblings.
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 explicitly explains when to use the tool (after user pastes token or to get login link), provides alternatives (adding token to config header for permanent login vs pasting for session-only), and gives clear usage scenarios. It also contrasts with session-only vs permanent connection, fully covering when and how to use.
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 advbox_* tools are clearly distinct by resource (customer, lawsuit, transaction, post, movement) and action (create, get, list, update). Overlapping tools like lawsuit_history, lawsuit_movements, and last_movements have clear scoping in descriptions. The platform tools (authenticate, connect, marketplace) are separate and well-defined.
The advbox_* tools follow a consistent verb_noun pattern (create_customer, get_lawsuit, list_transactions). The non-advbox tools (authenticate, connect, marketplace) use different naming but are auxiliary and have clear names. Minor deviation but overall predictable.
With 26 tools, the set is on the heavy side, but the legal practice domain is broad, covering customers, lawsuits, transactions, posts, and movements, plus platform management tools. Each tool has a defined role, though some could be consolidated (e.g., the multiple movement-related list tools).
Core workflows for customers, lawsuits, and transactions are covered with create/get/list/update, but there are missing operations: no update_customer, no deletes for any resource, no get_post or update_post despite list and create. The settings tool helps discover IDs, but the lifecycle is incomplete.