Repository navigation
Conversation
The docs said the buckets are public and need no credentials, but never that egress is free (the Google Public Data Program and AWS Open Data Sponsorship Program cover it). Worse, the always-on MCP instructions said "warn before any download", which an agent can read as a cost warning. State that downloads are free in the user guide, idc://guide, INSTRUCTIONS and the get_cohort_urls description, and say the size check is about transfer time and disk space. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
There was a problem hiding this comment.
🟢 Approval recommended
The wording-only changes are consistent across both audiences, with no identified blocking issues.
No open issues 🎉
What changed in this PR
Clarifies for users and MCP agents that IDC downloads have no egress fees, while preserving size checks for transfer time and disk space.
Changes:
- Adds download-cost guidance to the user guide.
- Mirrors the clarification in MCP instructions, the guide resource, and tool documentation.
- Leaves runtime behavior and API contracts unchanged.
| File | Description |
|---|---|
| src/idc_api/mcp/server.py | Clarifies download costs and size warnings for agents. |
| docs/user-guide.md | Explains free downloads and practical size considerations. |
Review effort: Balanced
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Nothing in the docs or agent-facing text said that downloading IDC data is free. The Google Public Data Program and the AWS Open Data Sponsorship Program cover egress fees (IDC docs). We only said the buckets were public and needed no credentials. Our "warn before any download" wording also made it likely an agent would tell users that downloads may be expensive.
What changed:
docs/user-guide.md: new "Downloading is free" paragraph in §4 (no billing, no cloud account, whether the data goes to a laptop, a cluster or a cloud VM). The size-check advice in the data-model section now says it's about transfer time and disk space, not cost.INSTRUCTIONS(always-on): rule 3 now says the download warning is about time and disk space, and that downloads are free (no egress fees). This adds about one line.idc://guide: the same clarification on the size-check line, plus a "Downloading is free" note in workflow step 4 telling the agent to reassure users who ask about cost.get_cohort_urlsdescription: "anonymous public URLs, free to download (no egress fees)".There's no CHANGELOG entry because only wording changed: no endpoints, tools, response shapes or config.
Test plan
pytest tests -q: 153 passed🤖 Generated with Claude Code