peek

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

No annotations are provided, but the description discloses key behaviors: it is a one-shot snapshot, does not return raw tool output, and has specific message extraction support for certain models. It also notes that tool calls are normalized and exclude raw output, which is a useful behavioral detail.

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 concise and front-loaded with the purpose, then quickly lists exclusions and supported model details. Every sentence earns its place, though one minor redundancy exists with 'not gapless streaming' and 'not a history API' being similar concepts, but it's acceptable.

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?

Given no output schema or annotations, the description does a thorough job of setting expectations: it clarifies what it returns, what it excludes, and its limitations. For a relatively simple observation window tool, this is complete for an agent to call it correctly.

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%, so parameters are well-documented in the schema. However, the description adds meaningful context beyond the schema: it clarifies that tool_calls are normalized and exclude raw output, and that message extraction is supported for specific models, which helps the agent understand the semantics of include_tool_calls and pids.

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 tool's purpose: a one-shot short observation window for running child agents, returning natural-language message events and optionally normalized tool_call events. It distinguishes itself from a history API, gapless streaming, and stdout/stderr tailing, clearly separating it from sibling tools like wait and get_result.

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?

Explicitly states what it is not (not a history API, not gapless streaming, not stdout/stderr tailing) and what it returns (only message events, optionally tool calls) in contrast to siblings like get_result or wait. It also gives context on when to use it: for a quick observation window rather than continuous monitoring.

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