stream_agent_run

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

No annotations are provided, so the description carries the full burden. It discloses that it collects the stream until server closes or timeout, and mentions timeout_seconds. But it does not explicitly state whether the operation is read-only or destructive, nor does it discuss authentication, rate limits, or side effects. The 'Fetch' verb implies a read, but it's not explicit.

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 highly concise: two introductory sentences and a structured Args list. Every sentence adds value without redundancy. The key action is front-loaded in the first line.

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 that an output schema exists (not shown), the description does not need to explain return values. It adequately covers the streaming nature (SSE events) and timeout behavior. However, it lacks context about prerequisites (e.g., run state) and does not clarify when the stream ends naturally, leaving minor gaps.

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?

The schema has 0% description coverage, meaning parameter meanings are entirely absent from the schema. The description's Args section adds essential meaning: examples for agent_id and run_id, and a clear description for timeout_seconds as 'HTTP timeout for the stream request'. This fully compensates for the missing schema descriptions.

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 'Fetch SSE events for a run' with the specific HTTP path, and it distinguishes itself from sibling tools like get_agent_run by noting it's for streaming events. The verb 'Fetch' and resource 'run' are explicit and unique among siblings.

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?

It provides an alternative: 'Prefer polling get_agent_run for long-lived watches,' which guides the agent when not to use this tool. However, it does not explicitly state when to use this tool (e.g., for real-time streaming), leaving some ambiguity.

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