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

The `readOnlyHint` annotation already covers safety, and the description adds meaningful behavior: it may block up to `wait_seconds` when the run is live with no new data, and it returns new comments plus an optional screenshot image. This is useful beyond the annotation.

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?

Three compact sentences, front-loaded with the core behavior, then pagination and wait semantics, then the screenshot option. There is no wasted text.

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?

With no output schema, the description still says what is returned: steps after the index, new comments, and optionally a screenshot. That is sufficient for invocation, though it does not detail the structure of each step.

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 only 40%, but the description compensates well by explaining `after` (use last index; -1 for all), `wait_seconds` (waits only if live and nothing new), and `include_screenshot` (adds latest screen as image). The remaining parameters are documented in the schema.

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 uses a specific verb and resource: it lets the agent follow a run step by step and return new steps/comments. It is clearly distinguishable from siblings like search_runs or live_streams, though it does not explicitly name alternatives.

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 operational guidance for pagination (`after`, `-1` for all) and waiting behavior, but does not explicitly state when to use this tool versus `live_streams`, `search_runs`, or `broadcast_step`. Usage is implied rather than fully routed.

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