{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreigfgz5zwpa5zu3euony3i23elw6cshu5ajdp3dfenwayvalayimre",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mo773a7lyst2"
  },
  "path": "/t/can-app-metadata-and-tool-descriptions-improve-how-chatgpt-discovers-tools-from-installed-apps/1382558#post_3",
  "publishedAt": "2026-06-13T20:36:16.000Z",
  "site": "https://community.openai.com",
  "tags": [
    "similarly vague"
  ],
  "textContent": "Hey there – good questions all around, I’m going to give you the vague answer, less because your question isn’t valid and more because the best practices have been extremely in flux, and as I’m sure you’ve heard about our plans to merge ChatGPT and Codex, many of my answers will change. My recommendation in general is to accept that there are _very few_ known best practices here besides:\n\n  1. Making the suggested intent of the tool clear to the model,\n  2. Leaning on model-written language for tool descriptions (models are generally fairly good at writing for themselves), and\n  3. Writing lots of evals + hill-climbing on them\n\n\n\nOur dev docs are similarly vague for this reason, and our apps/plugin-writing teams all find new successful practices on a daily basis. That’s of course not to say you should give up on learning to build on the models, and more to say that the only way to truly learn them is to try things, and try things constantly.",
  "title": "Can app metadata and tool descriptions improve how ChatGPT discovers tools from installed Apps?"
}