fix: improve command descriptions for LLM tool discoverability (round 2)#65
Merged
CodesMcCabe merged 2 commits intomainfrom Apr 16, 2026
Merged
fix: improve command descriptions for LLM tool discoverability (round 2)#65CodesMcCabe merged 2 commits intomainfrom
CodesMcCabe merged 2 commits intomainfrom
Conversation
Target three eval failures (transfers 0%, portfolio 0%, webhooks-create 67%): - wallet address: add explicit deflections to transfers/portfolio/nfts - transfers: lead with "transfer history", add USE WHEN pattern - balance: deflect to portfolio tokens for multi-network queries - portfolio tokens: lead with cross-network signal, add USE WHEN pattern - webhooks create: amplify write/create signal with (write operation) - webhooks list: strengthen read-only contrast with create Co-Authored-By: Claude Sonnet 4.6 (1M context) <[email protected]>
blakecduncan
approved these changes
Apr 16, 2026
Co-Authored-By: Claude Sonnet 4.6 (1M context) <[email protected]>
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Targeted fixes for 3 eval failures from run
cli-anthropic-1776364842452(91.4% → target ≥97%):alchemy wallet address— added explicit deflections totransfers,portfolio tokens, andnftsso "wallet" queries don't incorrectly land herealchemy transfers— rewritten to lead with "transfer history" + USE WHEN pattern (was being confused withwallet address)alchemy balance— now deflects toalchemy portfolio tokensfor multi-network/portfolio queries (was absorbing portfolio queries)alchemy portfolio tokens— leads with "cross-network portfolio" signal + USE WHEN patternalchemy webhooks create— amplified write/create signal with "(write operation)" + USE WHEN/DOES NOT contrastalchemy webhooks list— strengthened read-only framing to contrast with createTest plan
pnpm run buildpasses (verified locally)--helpoutput for each changed command🤖 Generated with Claude Code