get_v1_1_FollowingUser Following / Light Group: User. Billing per call: 1 Credits.
| Name | Required | Description | Default |
|---|---|---|---|
| id | No | Exactly one of User ID or Username must be provided. | |
| count | No | Number of results. Max: 200 | |
| cursor | No | ||
| username | No | Exactly one of User ID or Username must be provided. |
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?
With no annotations provided, the description must disclose behavioral traits like pagination, authentication, rate limits, or output shape. It only mentions billing, which is not operational behavior. The word 'Light' hints at a reduced feature set but never specifies what is omitted.
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 extremely short, but the brevity is not effective conciseness—it omits critical information to the point of being unhelpful. 'Group: User' and billing info are not actionable for invoking the tool correctly, so the sentences do not 'earn their 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?
Given the tool has 4 parameters, no output schema, and no annotations, the description should provide substantial context about return structure, pagination, and any special constraints. It provides none, making it wholly inadequate for an agent to use safely or 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 description adds no parameter semantics beyond the input schema. The schema already covers the id/username mutual exclusivity and count max, but the description does not elaborate on cursor usage or clarify any edge cases. With 75% schema coverage, the description should compensate for missing details (e.g., cursor semantics) but entirely fails to do so.
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 'User Following / Light' is a label rather than an explicit statement of function. It lacks a clear verb (e.g., 'retrieve') and gives no indication of what data is returned (user objects vs. IDs). It does not distinguish itself from siblings like get_v1_1_FollowingIds or get_v2_Following.
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?
There is no guidance on when to use this tool versus alternatives. No exclusions, prerequisites, or context about the 'Light' variant are provided, leaving the agent without any basis to select it over sibling tools.
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 appear to do the same thing, such as get_v1_1_Followers vs get_v2_Followers and get_v2_Tweet vs get_v2_TweetDetail. The descriptions are too brief to clarify differences, and multiple user lookup tools (get_v1_1_Users, get_v2_UserByRestId, etc.) create confusion.
Naming is inconsistent, mixing camelCase (get_ShortUrl), snake_case (get_email_search_by_username), and version prefixes with varying formats (get_v1_1 vs get_v2). No uniform verb_noun pattern is followed.
With 32 tools, the server is overloaded, especially given many redundant variations across API versions. The count exceeds the 25-tool threshold for too many tools, and many could be consolidated.
The server is entirely read-only (all tools are GET), missing write operations like posting tweets, following users, or sending direct messages. This is a significant gap for a Twitter server, and even read coverage has redundancies rather than comprehensive distinct endpoints.