tweetapi_user_tweets_and_repliesRequires a TweetAPI API key and consumes normal TweetAPI quota. Read-only; one upstream request per call. The model must request pagination cursors explicitly. Fetch one page of public tweets and replies from a user timeline.
| Name | Required | Description | Default |
|---|---|---|---|
| cursor | No | ||
| userId | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds valuable behavioral context: it requires an API key, consumes normal TweetAPI quota, makes one upstream request per call, and requires explicit pagination cursor requests. This goes beyond the annotations and helps the agent understand side effects and constraints.
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 three sentences and around 45 words, covering the essential operational details. It is reasonably concise, though the first sentence mixes auth, quota, and read-only information, and the actual purpose is saved for the last sentence. Still, no extraneous words; each sentence contributes to operational understanding.
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 no output schema and two parameters, the description covers key operational concerns: authentication, quota, read-only behavior, single upstream request, pagination handling, and one-page scope. It does not describe the return payload structure or sorting, but for a simple fetch operation with strong annotations, it provides enough context for selection and basic invocation.
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 input schema has 0% description coverage, so the description carries the burden. It explains that `cursor` is for pagination and that the tool fetches one page, which gives some meaning. However, it does not explicitly define `userId` as the numeric Twitter user ID (though the pattern `^\d+$` hints at it) or explain how to obtain and use cursors. Partial compensation, but gaps remain.
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 fetches 'one page of public tweets and replies from a user timeline,' using a specific verb ('Fetch'), resource ('tweets and replies from a user timeline'), and scope ('one page'). This distinguishes it from the sibling tool `tweetapi_user_tweets`, which likely returns only tweets without replies.
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 provides context about API key requirements, quota consumption, and the need to explicitly request pagination cursors. However, it does not explicitly state when to use this tool over alternatives (e.g., `tweetapi_user_tweets`) or mention exclusion criteria. Usage is implied but not clearly contrasted with 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 have overlapping or unclear boundaries: tweetapi_user_followers_v2 and tweetapi_user_followers_list both fetch followers with nearly identical descriptions, and tweetapi_docs_search overlaps with tweetapi_endpoint_lookup. Additionally, tweetapi_user_about_account and tweetapi_user_by_username both retrieve user info by username, creating confusion.
All tools share the 'tweetapi_' prefix and follow a consistent resource_specific pattern (e.g., tweetapi_tweet_details, tweetapi_user_followers_ids). The use of lowercase with underscores is uniform, and there is no mixing of camelCase or inconsistent verb styles.
With 38 tools, the server is overstuffed. Many tools are redundant (e.g., three follower variants, three documentation-related tools), which inflates the count beyond what is needed for a read-only Twitter API wrapper. A leaner set of 15-20 tools would be more appropriate.
The read-only API surface is well covered: tweets (details, metrics, quotes, retweets, translate, search), users (profiles, followers, following, subscriptions, verified followers), lists, communities, and spaces. Minor gaps exist (e.g., no direct 'get user mentions' or list lookup by slug), but core workflows are fully supported.