Back-Agent MCP Server

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

With no annotations provided, the description carries full burden and delivers substantial behavioral context. It discloses key traits: creates non-blocking background tasks, returns task ID immediately, allows up to 3 concurrent tasks by default, and clarifies what it doesn't do (no direct shell execution, no raw stdout/stderr). However, it doesn't mention error handling, retry behavior, or resource constraints beyond concurrency limits.

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?

The description is well-structured with clear sections (IMPORTANT warning, What it does, What it does NOT do) and every sentence adds value. It's appropriately sized for a complex tool but could be slightly more concise by integrating some repetitive elements about not being a shell executor. The front-loaded warning is particularly effective.

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?

For a complex tool with no annotations and no output schema, the description provides substantial context about behavior, limitations, and integration with sibling tools. It explains the return value (task ID) and how to use it with other tools. The main gap is lack of information about error responses or what happens when concurrency limits are exceeded, but overall it's quite 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?

Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description doesn't add meaningful parameter semantics beyond what's in the schema - it mentions 'natural language task description' and 'background task' but these are already covered in the schema's task parameter description. The baseline of 3 is appropriate when the schema does the heavy lifting.

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 explicitly states what the tool does: 'Spawns Claude Code (an AI coding agent) as a subprocess to complete development tasks in the background.' It clearly distinguishes from sibling tools by emphasizing it's NOT a direct shell command executor (unlike execute-task) and specifies it creates background tasks that require get-task-status/result for monitoring (unlike list-tasks or get-task-stats). The verb+resource combination is specific and unambiguous.

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 guidance on when to use this tool versus alternatives. It states 'NOT a direct shell command executor' (contrasting with execute-task), specifies it's for 'background tasks' with natural language requests, and directs users to use get-task-status and get-task-result for tracking and retrieval. The 'What it does NOT do' section clearly sets boundaries against misuse.

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