Loading ToolBench
Social media content generation and analysis API + MCP server. Generate hashtags, captions, content ideas, and analyze engagement — all rule-based, no external AI APIs.
Social Media Toolkit has well-structured tool definitions with complete input schemas and clear descriptions. All 9 tools are explicitly registered with proper JSON Schema. Naming follows verb_noun convention (generate_*, calculate_*, get_*, estimate_*). However, output schemas are not documented, LLMs cannot predict response structure. Parameter descriptions are present but often minimal (e.g., 'Number of likes' lacks context on what the metric means). No error handling guidance, no recovery paths, and no indication of which tools are idempotent or safe to retry. Missing tool annotations (readOnlyHint, destructiveHint). All tools are read-only (low risk), but this should be explicit in metadata.
Calculate engagement rate from likes, comments, shares, saves, and follower count.
Calculate follower growth rate and project future growth.
Estimate time to reach follower milestones based on current growth.
Generate a social media caption with hook, body, and CTA.
Generate content ideas for a specific niche with format suggestions.
Generate relevant hashtags for a topic. Supports platform-specific limits and competition filtering.
Get optimal posting times for a social media platform, with timezone conversion.
No output schemas documented. LLMs cannot predict response structure, forcing them to guess what fields are returned and how to chain tools. E.g., does generate_hashtags return {hashtags: []} or {results: {tags: []}}?
No error handling guidance. Tools lack recovery hints (e.g., 'If timezone is invalid, try UTC or a major city timezone'). Agents cannot self-correct on failures.
Parameter descriptions are minimal and lack context. E.g., 'Number of likes' does not explain what the metric represents or how it's used in calculations. 'Topic for the caption' is vague, does it accept free text or specific keywords?
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 54 | 2026-07-28+ | v2 |
List all available hashtag categories and platform limits.
Score content performance based on weighted engagement metrics.
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). All tools are read-only and safe to retry, but this is not declared. Agents cannot optimize retry logic or warn users about side effects.
get_categories has minimal description ('List all available hashtag categories and platform limits') and no explanation of when to call it or what structure it returns. Discovery tools should guide agents on usage.