get_highlightsGet instagram user highlights by id_highlight. id_highlight can be obtained from the request to get the "User Highlights tray" Billing per call: 1 Credits.
| Name | Required | Description | Default |
|---|---|---|---|
| id_highlight | No | Highlight ID |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It adds billing cost ('1 Credits') and the prerequisite for obtaining the ID, but doesn't describe return format, authentication, or potential errors. For a simple read operation, this is minimal but not misleading.
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 two short sentences, front-loaded with the purpose. Every sentence adds value: the first defines the operation, the second explains how to get the parameter and the cost. No unnecessary fluff.
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 tool with one parameter and no output schema, the description covers the purpose, parameter source, and cost. It could mention what the response contains, but the tool name and purpose make that obvious. Overall, sufficiently complete for its complexity.
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 coverage is 100% with a basic 'Highlight ID' description. The description adds valuable provenance information—that the ID comes from the User Highlights tray request—which helps the agent understand the parameter's source and format 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 clearly states the tool retrieves Instagram user highlights by ID, with a specific verb (Get), resource (user highlights), and parameter (id_highlight). It distinguishes from sibling tool get_highlights_tray by indicating this is for a specific highlight ID, not the tray.
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 clear prerequisite context: the id_highlight can be obtained from the 'User Highlights tray' request. This tells the agent when/how to use the tool, though it doesn't explicitly mention alternatives or when not to use it.
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.
Many tools have overlapping or near-identical purposes (e.g., get_posts vs get_posts_username, get_reels_posts vs get_reels_posts_username). The distinction between get_post_info, get_post_info_v2, get_reel, and get_tv_info is unclear from descriptions alone. This will cause frequent misselection.
Naming is inconsistent: suffixes like '_username', '_hd', '_v2', '_id' appear sporadically, and the same resource type is named differently (e.g., 'posts' vs 'post_info' vs 'reels_posts' vs 'tv_posts'). Some tools are meta (get_requests, get_server) and deviate from the data-focused pattern. Overall, no clear naming convention.
With 40 tools, the set is overly large for an Instagram scraper. Many tools are near-duplicates differing only by input type (ID vs username), which could be consolidated. The count far exceeds the typical 3-15 range and feels bloated, though not extreme.
The tool set covers a comprehensive range of Instagram data: user info, posts, reels, TV, stories, highlights, comments, likes, followers, followings, hashtag/location/music search, and even server status. Despite some vague tools (get_additional_info, get_basic_engagement), it appears functionally complete for the domain.