# Tavily Claude Code CLI Evaluation

**Category:** Search
**Score:** 81 (B)

This is the agent-readable Devtool Arena evaluation page for Tavily on Claude Code CLI.

## Summary

| Metric | Value |
|--------|-------|
| Status | completed |
| Overall score | 81 |
| Grade | B |
| Eval score | 84 |
| Discovery score | 75 |
| Cost | $0.19 |
| Runtime | 1m 45s |
| Tool calls | 16 |
| Errors | 0 |
| Tokens used | 446793 |
| Success | Yes |

## Agent-Readiness Checklist

| Signal | Evidence |
|--------|----------|
| Context7 | Not found |
| llms.txt | Not found |
| MCP server | Not found |
| Typed SDK | Not found |
| OpenAPI | Not found |
| Agent skills | Not found |
| CLI | Not found |

## Evaluation Prompt

````text

# Task
Using the tvly CLI (Tavily), run a small research workflow:

1. Run TWO related searches to build a picture of a topic:
   a. A broad query: "grid-scale battery storage advances"
   b. A more specific, recency-focused query: "grid-scale battery storage breakthroughs 2025"
2. Merge the results from both searches, deduplicate by URL, and select the top 5 most relevant results
3. If the CLI supports fetching/extracting page content, use it to retrieve the full content of the single most relevant result, then write a 2-3 sentence summary that is grounded in that fetched content (not just the snippet)
4. Format the output as JSON with two keys:
   - "results": the top 5 deduplicated results, each with title, URL, and snippet/description
   - "summary": your grounded 2-3 sentence summary of the top result (include the source URL)

Use the CLI directly, not Python SDK calls.

You MUST use the `tvly` CLI to accomplish this task.
Do NOT write Python scripts that import the SDK — use CLI commands via the terminal.

If you need help with CLI commands, check the documentation: https://docs.tavily.com/documentation/tavily-cli
You can also use `tvly --help` and `tvly <command> --help` to discover available commands.

## Setup
You need to install and authenticate the `tvly` CLI yourself.

### Installation
Run: `curl -fsSL https://cli.tavily.com/install.sh | bash`

### Authentication
The following environment variables are already set in this environment: `TAVILY_API_KEY`
The CLI should pick these up automatically, or pass them to commands as needed.

## Execution
1. Install the `tvly` CLI using the command above
2. Verify the installation: `tvly search '*****' 2>&1 | head -5`
3. Authenticate using the credentials above
4. Perform the task described above

Work in the /home/daytona/app directory. Run commands and print output to stdout.
If there are errors, debug and fix them until the task runs successfully.

## Summary
When you are done, write a JSON summary file to /home/daytona/app/results.json with this structure:
{
  "operations": [
    {"step": 1, "description": "What you did", "command": "the CLI command", "success": true/false, "output_summary": "brief result"},
    ...
  ],
  "overall_success": true/false,
  "notes": ["any relevant notes about the execution"]
}

````

## Grader Results

| Check | Passed | Weight | Score | Details |
|-------|--------|--------|-------|---------|
| Stage 2 Auth | Yes | — | 25 | — |
| Stage 3 Task | Yes | — | — | — |
| Stage 1 Install | Yes | — | 5 | — |
| Stage 5 Llms Txt | Yes | — | 5 | — |
| Stage 0 Cli Exists | Yes | — | 5 | — |
| Stage 4 Json Output | Yes | — | 15 | — |
| Stage 6 Agent Skill | Yes | — | 20 | — |
| Stage 3 Non Interactive | No | — | 0 | — |

## Run Artifacts

| Artifact | Value |
|----------|-------|
| Conversation turns | 24 |
| Tool call traces | 16 |
| Generated files | 1 |
| Exit code | — |
| Completed at | 2026-09-27T14:05:34.601113+00:00 |

### Generated Files

- /home/daytona/app/results.json

## Related Pages

- [Claude Code CLI leaderboard](/leaderboard/claudecode/cli)
- [Compare Claude Code CLI companies](/leaderboard/claudecode/cli/compare)
- [Agent Landscape](/leaderboard/discoverability)

Canonical URL: https://devtoolarena.com/claudecode/cli/tavily