launch_status

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

With no annotations, the description carries the full burden. It clearly discloses that the tool is non-blocking, reads from a run log, returns ordered events, and defaults to the newest run. It does not mention error behavior or response format details, but the core behavioral traits are well covered.

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 compact and front-loaded: main action, then return contents, then default behavior, then rationale. Every sentence adds value and there is no filler or repetition of the tool name.

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 simple read-only tool with one optional parameter, the description is nearly complete. It explains what the run contains, the default behavior, and why it reads from the log. It could go slightly deeper on the exact event shape, but the absence of an output schema is mitigated by the high-level return description.

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 single run_id parameter already explains that it comes from check, fix, or call_provider_tool, and that omission means newest run. The tool description restates the default but adds no new parameter-level meaning.

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 states a clear verb and resource: 'Read a run back without waiting on it', and explains the tool returns ordered events. It is distinct from siblings like check or fix because it is explicitly a non-blocking read of a previous run, though it does not name a specific sibling to differentiate from.

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 gives strong context: reads progress from the run log rather than holding a call open, and defaults to the newest run. It implies this should be used after check or fix when a long-running operation has been kicked off, but it does not explicitly name alternatives or exclusion criteria.

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