claude_run

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It discloses caching of Anthropic auth and notes that working_directory is ignored for safety. However, it does not describe output format, error handling, or rate limits, which are gaps for a tool with no annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, no redundancy. First sentence states purpose, second gives usage context, third mentions auth. Every sentence earns its place. Front-loaded with the most critical information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description adequately covers purpose, usage context, auth, and one parameter note, but given no output schema and no annotations, it is missing output format, error handling, and model availability details. Adequate but not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All 4 parameters have schema descriptions (100% coverage). The description adds value beyond the schema by explaining the authentication caching, the default timeout (60s), and that working_directory is ignored for Claude. This extra context helps the agent use parameters correctly.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Send' and resource 'prompt to Claude via local Claude Code CLI'. It explicitly distinguishes from sibling tools like codex_run, gemini_run, and local_llm_run by specifying when to use: when the MCP client is not Claude or for cross-checking results.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit usage guidance: 'Use this when the MCP client is NOT Claude (e.g. Cursor, Windsurf, Zed) or for cross-checking results from other AI backends.' It lacks explicit when-not-to-use but the positive cases are clear and imply alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.