mcp: embed example calls in top-level tool descriptions (#723)
* mcp: embed example calls in top-level tool descriptions
agents (esp. claude sonnet) hallucinate param names from training-data
priors — `pr_number` instead of `pull_number`, `summary` instead of
`body`, full subcommand strings jammed into `git({command})` like it
were `shell({command})`. each error burns a tool round-trip plus a
follow-up ToolSearch, ~40+ events / 24h, no observable recovery cost
to us but visible to users in agent logs.
cheapest fix: add a sample formatted function call to every affected
tool's top-level description. example anchors are more reliable than
schema descriptions alone because the model treats descriptions as
narrative but call examples as canonical structure. for `git` and
`shell` (whose `command` fields collide), include explicit
counter-examples disambiguating which tool owns which shape.
no schema aliases / coercion yet — try the cheap thing first; if the
next audit window still shows the same hallucination rate, layer
aliases on top per #585's recommendation.
closes #585, closes #701
* mcp: drop negative anchors from tool descriptions
negation is a footgun in tool descriptions — telling the model "NOT
pr_number" makes pr_number more salient, not less. let the positive
example carry the schema and trust the model to read it.
removes:
- "the parameter is pull_number (a number), NOT pr_number" and
similar across checkout_pr, get_pull_request, list_pull_request_reviews,
get_review_comments, create_pull_request_review
- "NOT summary, message, or content" on report_progress
- "WRONG: git({ command: 'log --oneline' })" counter-example on git
- redundant param-type restatements after the example (e.g. "depth is a
number, not a string" on git_fetch, "description is required" on shell)
keeps a single positive example per tool. for tools with multiple call
shapes (git, git_fetch, push_branch), two positive examples instead of
one + a counter-example.
This commit is contained in:
committed by
pullfrog[bot]
parent
868576a474
commit
b8ac42e875
+2
-1
@@ -15,7 +15,8 @@ export function CommitInfoTool(ctx: ToolContext) {
|
||||
name: "get_commit_info",
|
||||
description:
|
||||
"Retrieve commit metadata and diff via GitHub API. Use this instead of git show for reviewing commits - " +
|
||||
"it works with shallow clones and shows the actual changes in the commit. Returns diffPath pointing to formatted diff file.",
|
||||
"it works with shallow clones and shows the actual changes in the commit. Returns diffPath pointing to formatted diff file. " +
|
||||
'Example: `get_commit_info({ sha: "2a6ab5d06ba64dd987bd88c4403287" })`.',
|
||||
parameters: CommitInfo,
|
||||
execute: execute(async ({ sha }) => {
|
||||
const response = await ctx.octokit.rest.repos.getCommit({
|
||||
|
||||
Reference in New Issue
Block a user