composer_agent

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

With no annotations provided, the description carries the full burden and does so thoroughly. It discloses shared settings (HOME, cwd, MCP, plugins, permissions), the ownership model, injected sub-agent properties, non-blocking dispatch, exit code semantics, no-polling/no-foreground behavior, and the reasoning_effort error. This is exceptional transparency far beyond typical descriptions.

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 long but densely informative, with each sentence contributing operational value and the core purpose front-loaded. However, it is a continuous block of Japanese text without structural breaks, which slightly hampers scannability despite the high information density.

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 tool with 7 parameters, no annotations, and an output schema, the description is remarkably complete. It covers the entire lifecycle: launch, turn sending, completion detection with exit codes, result retrieval, and parameter restrictions, leaving no major operational gap.

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% and the schema already explains each parameter, including defaults, semantics, and error conditions (e.g., reasoning_effort). The description adds some workflow context but largely reiterates what the schema states, so the baseline 3 is appropriate.

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 opening sentence explicitly states the tool launches the Grok Build Composer model interactive agent TUI on a persistent terminal, naming the default model (grok-composer-2.5-fast). This is a specific verb+resource that clearly distinguishes it from sibling agent launchers like claude_agent, codex_agent, and grok_agent.

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 strong operational context: it instructs to fire-and-forget (parent does not wait), send turns via pty_send, receive completion via wait_command or aiterm-wait with exit codes, and collect results via pty_read. However, it does not explicitly name alternatives or state when not to use this tool, falling short of a 5.

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