get_base_apitools_followSee details https://developer.x.com/en/docs/twitter-api/v1/accounts-and-users/follow-search-get-users/api-reference/post-friendships-create Group: follows. Billing per call: 1 Credits.
| Name | Required | Description | Default |
|---|---|---|---|
| ct0 | No | ||
| userId | No | ||
| proxyUrl | No | ||
| resFormat | No | ||
| auth_token | No | ||
| screenName | 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?
No annotations are provided, so the description must carry the full burden of behavioral disclosure. It only states the billing cost and links to external docs. It does not disclose that this is a mutating operation (following), any side effects, authentication requirements, or rate limits.
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 short but not concise in a useful sense. It wastes space on a URL and billing without conveying core purpose. It is under-specified rather than efficiently informative.
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 6 undocumented parameters, no output schema, no annotations, and a complex domain (Twitter API), the description is completely inadequate. It provides essentially no actionable information.
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 0% and the description provides no explanation of any of the 6 parameters. The parameters (ct0, userId, proxyUrl, etc.) are entirely undefined, so an agent would have no clue how to populate them.
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 does not explicitly state what the tool does. It only provides an external URL and billing information. The title 'to follow' is vague, and while the URL hints at creating a friendship (following), the description itself lacks a clear verb-resource statement. It does not distinguish from the many sibling tools.
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 mention of prerequisites, exclusions, or comparisons to other follow/unfollow tools. The description is purely a URL reference and billing note.
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 set is full of confusing variants such as get_/post_ prefixed duplicates of the same endpoints, competing V1/V2 versions of the same action (e.g., followersList vs. followersListV2), and poorly described tools like CommunitiesSearchV2 and getCt0 that give no clear unique purpose. Agents would frequently need to guess between similar tools for a single task.
Naming is chaotic, mixing camelCase (getDMS, likeV2), PascalCase (CreateNoteTweet, CommunitiesMemberV2), and inconsistent prefixes (gettools_*, get_*, post_*) with duplicated operations. The 'get_/post_' prefixes appear to indicate API method rather than action, but they are applied inconsistently, with some tools appearing under both and others only once. There is no predictable verb_noun pattern throughout.
With 107 tools, the server is extremely large, far exceeding the 50+ threshold for extreme mismatch, and this count is inflated by duplicates (many get_/post_ twins) and overlapping V1/V2 variants. Even the unique tool set is likely around 60-70, which is still an unwieldy surface for an agent to negotiate. This severely disrupts coherence.
The tool set covers most core Twitter/X domains: tweets, likes, retweets, follows, DMs, search, communities, lists, and profile management. However, it is cluttered with duplicates and lacks some obvious pieces like mute/unmute operations or a direct 'update tweet' action, and several tools appear to be thin wrapper variations of the same endpoint. Coverage is broad but not cleanly organized.