get_follow_graphWho a contestant currently follows and who follows them among their castmates (Instagram) — the data behind Follow Watch. For unfollows, use get_follow_events.
| Name | Required | Description | Default |
|---|---|---|---|
| show | Yes | Season ID or slug, e.g. "12" or "love-island-usa-season-8". Use list_shows to discover. | |
| contestant | Yes | Contestant ID or slug, e.g. "394" or "amora-cachee". |
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 covers safety, and the description adds useful context: it is a point-in-time Instagram edge snapshot scoped to castmates. However, it does not disclose output shape, possible absence of one side of the graph, or how the 'current' snapshot is maintained, so it stays at baseline rather than rising much.
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 core behavior is front-loaded in the first sentence, and the second sentence provides a useful pointer to an alternative tool. There is no redundant explanation of the parameters or repetition of the schema.
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 low-complexity, read-only tool with two well-documented parameters, the description is complete enough for an agent to select and call it correctly. It communicates what the result represents, the scope of the graph, and the key sibling to use for a different need.
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%, and both parameters already have clear descriptions with ID/slug examples and discovery guidance. The description does not need to add parameter details for the agent to invoke the tool correctly.
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 states a specific verb and resource: it retrieves who a contestant currently follows and who follows them among their Instagram castmates. This clearly distinguishes it from get_follow_events, which is the historical/unfollow counterpart.
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 phrase 'currently' establishes that this is for the present snapshot of the follow graph, and it explicitly says 'For unfollows, use get_follow_events.' This gives the agent a clear routing decision between the two most confusable 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.
Each tool targets a distinct resource or analysis need: cast summaries, single-contestant details, follower time series, follow/unfollow events, follow graph, trend events, and export output are cleanly separated. The descriptions explicitly cross-reference related tools, so an agent should be able to pick the right one without ambiguity.
Tool names follow a consistent get_/noun and list_noun pattern, with export_season_csv as the only slight variation—but it still clearly uses verb_noun convention. camelCase is avoided, and duplicate or vague verbs are absent.
Twelve tools is a well-scoped size for a read-only analytics data API. Each tool contributes a meaningful slice of the domain—discovery, show details, cast metrics, raw series, events, graphs, trends, usage, and export—without redundancy or bloat.
The surface covers the full read-only workflow: discover shows and seasons, list episodes, inspect contestants and cast, retrieve follower histories, engagement, follow relationships, trend events, and export a citation-ready CSV. No obvious lifecycle dead ends exist since the API is inherently data-access-oriented rather than CRUD.