peek

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

No annotations provided, so description carries full burden. Discloses one-shot nature, short window, and specific features/limitations: v1 model support, low-precision Forge tool calls, exclusion of raw output. Comprehensive.

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?

Description is somewhat lengthy but well-structured and front-loaded with core purpose. Each sentence adds unique value with minimal redundancy.

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?

Without output schema, description explains return values well (messages and optional tool calls) and addresses supported models and limitations. Could specify 'normalized' format more, but sufficient.

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 coverage is 100%, but description adds context: pids from run with dedup and not_found handling, peek_time_sec defaults and max, include_tool_calls defaults and what normalized tool calls include.

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?

Clearly states it's a one-shot observation window for running child agents, returning natural-language messages and optionally normalized tool calls. Distinguishes from history API, gapless streaming, and stdout/stderr tailing.

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?

Implies usage for short observation but does not explicitly compare to sibling tools like get_result, wait, or list_processes. Does not state when not to use it.

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