vital_get_user_latest_infoGet the latest device/app info reported for a user. Vital API: GET /v2/user/{user_id}/info/latest.
| Name | Required | Description | Default |
|---|---|---|---|
| user_id | Yes | The Vital user id (UUID). |
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 readOnlyHint annotation already declares the operation safe, and the description adds the 'latest' semantics plus the exact endpoint. However, it does not disclose behavior for cases where no info is reported, the shape of the returned payload, or any provider-specific quirks.
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?
A single sentence conveys the core purpose and the technical endpoint with no filler or redundancy. It is front-loaded with the action and resource, and the endpoint reference earns its place.
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, read-only, single-parameter tool, the description plus annotation and full schema coverage are largely sufficient. The lack of an output schema means a brief note about the returned structure would improve completeness, but it is not a critical gap for invoking the tool.
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?
Schema description coverage is 100%: the single required user_id parameter is already documented as 'The Vital user id (UUID).' The description only echoes the user_id path variable in the endpoint, adding no extra meaning beyond the 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 uses a specific verb ('Get') and a specific resource ('latest device/app info reported for a user'), and it provides the exact API endpoint. It does not explicitly name sibling alternatives, but the phrase 'device/app info' distinguishes it from profile/user-read tools like vital_get_profile and vital_get_user.
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?
No guidance is given about when to use this tool versus siblings such as vital_get_profile, vital_get_user, or vital_get_user_connected_providers. The endpoint is stated, but there is no context about appropriate use cases, prerequisites, or exclusion 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.
Each tool maps to a unique resource/action pairing—users, health summaries, timeseries, providers, and lab orders—so an agent can reliably distinguish them. Even similarly named getters are separated by the data domain (activity/body/sleep/workouts) and description.
All tools use the vital_ prefix and snake_case verb_noun forms, which is highly predictable. Minor inconsistency: get is used for both single-resource fetches and list-returning calls (get_workouts, get_user_connected_providers) while list is reserved for global collections.
21 tools is on the heavier side, but the breadth of the Vital API—users, providers, many health summary types, timeseries, and lab tests/orders—justifies most of them. It is slightly over a typical focused MCP server but not bloated or redundant.
The read side is strong: users, providers, summaries, timeseries, lab tests, and results are all covered. However, there are no update/delete user operations and no way to create a lab-test order, so core lifecycle/workflow gaps remain.