Colin McDonnell
b8ac42e875
* 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.
38 lines
1.1 KiB
TypeScript
38 lines
1.1 KiB
TypeScript
import { type } from "arktype";
|
|
import type { ToolContext } from "./server.ts";
|
|
import { execute, tool } from "./shared.ts";
|
|
|
|
export const GetIssueComments = type({
|
|
issue_number: type.number.describe("The issue number to get comments for"),
|
|
});
|
|
|
|
export function GetIssueCommentsTool(ctx: ToolContext) {
|
|
return tool({
|
|
name: "get_issue_comments",
|
|
description:
|
|
"Get all comments for a GitHub issue. Returns all comments including the issue body and all subsequent discussion comments. " +
|
|
"Example: `get_issue_comments({ issue_number: 1234 })`.",
|
|
parameters: GetIssueComments,
|
|
execute: execute(async ({ issue_number }) => {
|
|
// set issue context
|
|
ctx.toolState.issueNumber = issue_number;
|
|
|
|
const comments = await ctx.octokit.paginate(ctx.octokit.rest.issues.listComments, {
|
|
owner: ctx.repo.owner,
|
|
repo: ctx.repo.name,
|
|
issue_number,
|
|
});
|
|
|
|
return {
|
|
issue_number,
|
|
comments: comments.map((comment) => ({
|
|
id: comment.id,
|
|
body: comment.body,
|
|
user: comment.user?.login,
|
|
})),
|
|
count: comments.length,
|
|
};
|
|
}),
|
|
});
|
|
}
|