feat(mcp): optional per-tool responseMapping.followUp workflow hint#416
Merged
Conversation
Add an opt-in `followUp` string to a tool's responseMapping. When set, DynamicMcpTools appends it to the tool result as a "WORKFLOW HINT" line. The calling agent sees, inside the output it just received, what to do next (e.g. "a professional prediction also needs odds, lineups, player stats — call them before replying"). This drives multi-step tool chains far more reliably than a pre-call tool description, which agents read but often don't act on. Purely additive: tools without followUp are unchanged.
keysersoft
enabled auto-merge (squash)
July 14, 2026 08:59
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 subscribe to this conversation on GitHub.
Already have an account?
Sign in.
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Add an opt-in
followUpstring to a tool'sresponseMapping. When set,DynamicMcpToolsappends it to the tool result as aWORKFLOW HINTline.Why
Agents (Claude, etc.) reliably read tool results but often ignore multi-step guidance in a tool description. When an analysis needs several tools (e.g. a "professional football prediction" = predictions + odds + lineups + player stats + injuries + h2h), the agent tends to stop after the first obviously-relevant call. Putting the "call X, Y next" directive inside the result the agent just received drives the full chain far more reliably.
Scope
ResponseMapping.followUp?: string(engine-types.ts).DynamicMcpTools: append it toresultTextwhen present (cached with the response).followUpare byte-for-byte unchanged. No other engine or tool affected.