No user-submitted related servers found.
Scored across 9 tools
Every tool has a clearly distinct purpose: generate_image vs edit_image are explicitly differentiated (text-to-image vs image-to-image), embed_text vs rerank_documents cover different RAG stages, and speech_to_text/text_to_speech are opposites. Descriptions even cross-reference each other to prevent misselection.
All nine tools follow a consistent snake_case verb_noun pattern (get_quota, edit_image, embed_text, generate_image, list_models, list_voices, rerank_documents, speech_to_text, text_to_speech). No deviations in casing or style.
Nine tools is well within the ideal 3-15 range, and each one earns its place by mapping to a distinct NaN API capability (quota, image, embedding, rerank, STT, TTS, model/voice listing). No redundant or filler tools.
Coverage is strong across multimodal operations (image gen/edit, embedding, rerank, STT, TTS) with supporting discovery tools (list_models, list_voices) and quota inspection. The only plausible gap is a text/chat completion tool for the listed models, but the surface otherwise has no dead ends.