# evaluate_search_quality

Incrementally index the project and run a set of expected-result search cases to measure retrieval quality.

Agent View of the PolicyLayer registry record for `evaluate_search_quality`. HTML page: https://policylayer.com/tools/0215andrewfeng-ace-mcp/evaluate-search-quality

## Facts

- Tool: `evaluate_search_quality`
- Server: ACE-MCP (`0215andrewfeng/ace-mcp`) — https://policylayer.com/tools/0215andrewfeng-ace-mcp.md
- Homepage: https://github.com/0215AndrewFeng/ACE-MCP
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "evaluate_search_quality",
    "arguments": {}
  }
}
```

## Why evaluate_search_quality is rated Low

Even though evaluate_search_quality only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

## Use case

AI agents call evaluate_search_quality to retrieve information from ACE-MCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches ACE-MCP:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "evaluate_search_quality": {}
  }
}
```

## Other tools on ACE-MCP (16)

- `clear_project_index` — Destructive — https://policylayer.com/tools/0215andrewfeng-ace-mcp/clear-project-index.md
- `warm_index` — Execute — https://policylayer.com/tools/0215andrewfeng-ace-mcp/warm-index.md
- `ask_codebase` — Read — https://policylayer.com/tools/0215andrewfeng-ace-mcp/ask-codebase.md
- `cache_stats` — Read — https://policylayer.com/tools/0215andrewfeng-ace-mcp/cache-stats.md
- `find_callees` — Read — https://policylayer.com/tools/0215andrewfeng-ace-mcp/find-callees.md
- `find_callers` — Read — https://policylayer.com/tools/0215andrewfeng-ace-mcp/find-callers.md
- `find_definition` — Read — https://policylayer.com/tools/0215andrewfeng-ace-mcp/find-definition.md
- `find_references` — Read — https://policylayer.com/tools/0215andrewfeng-ace-mcp/find-references.md
- `get_file_snippet` — Read — https://policylayer.com/tools/0215andrewfeng-ace-mcp/get-file-snippet.md
- `get_summary` — Read — https://policylayer.com/tools/0215andrewfeng-ace-mcp/get-summary.md
- `index_project` — Read — https://policylayer.com/tools/0215andrewfeng-ace-mcp/index-project.md
- `list_symbols` — Read — https://policylayer.com/tools/0215andrewfeng-ace-mcp/list-symbols.md
- `project_stats` — Read — https://policylayer.com/tools/0215andrewfeng-ace-mcp/project-stats.md
- `search_context` — Read — https://policylayer.com/tools/0215andrewfeng-ace-mcp/search-context.md
- `generate_summary` — Write — https://policylayer.com/tools/0215andrewfeng-ace-mcp/generate-summary.md
- `resolve_projects` — Write — https://policylayer.com/tools/0215andrewfeng-ace-mcp/resolve-projects.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=0215andrewfeng-ace-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/0215andrewfeng-ace-mcp