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 practical behavioral context beyond the annotations: it explains the browser login flow, token copying, permanent vs session-only login, and how to use the returned auth link. It does not fully describe the output/return behavior, but this is not required given the simple optional-token interface and idempotentHint annotation.
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 dense, and the admin side of the flow is clearly separated from the agent-facing call. The phrasing is slightly informal ('paste', 'log in in the browser'), but there is no significant redundancy.
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?
The tool is simple with one optional parameter and no output schema, and the description covers both the permanent and session-only authentication paths as well as the user interaction flow. It could be more precise about what the no-argument call returns, but the essential behavior 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?
The schema provides only a string parameter 'token' with no description. The tool description compensates well by explaining that token is a JWT, that it is optional, how to call with it ('{ token: "<jwt>" }'), and when to call without it. This adds meaningful parameter semantics beyond the bare 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 indicates the tool handles authentication/login: 'log in in the browser, copy the access token' and supports both permanent and session-based login. It does not explicitly distinguish itself from the sibling 'connect' tool, but its purpose is reasonably specific to authentication.
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 gives explicit guidance on when to use which option: adding the token to server config for permanent access, or pasting it for a session-only login. It also specifies calling with 'no args to get the link', directly instructing the agent on the correct invocation steps.
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.
Several tools have overlapping purposes, particularly the wearable data tools (dietaai_libre_data, dietaai_sibionics_data, dietaai_sibionics_glucose) and the diary-related tools (dietaai_diary, dietaai_diary_logs, dietaai_diary_scheme). The distinctions are subtle and may confuse agents.
The naming is inconsistent: many tools use the 'dietaai_' prefix with noun-based names, while others like 'authenticate', 'connect', 'marketplace', 'report_bug', 'show_version', and 'toolkit_info' break the pattern entirely. The mix of English and Portuguese further reduces consistency.
With 19 tools, the server is on the higher end of the typical range. While it covers a broad domain (diet tracking, wearable integrations, marketplace), the count is borderline and could feel heavy.
The server focuses heavily on reading data (profiles, diary, foods, goals, wearable data) but lacks obvious write operations like updating goals, deleting diary entries, or modifying user settings. The single log tool (dietaai_log) is the only write path, leaving notable gaps for a full lifecycle.