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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds genuine value by describing the payload fields (including agent family), which matters since there is no output schema. It does not disclose result volume, ordering, or whether the snapshot is paginated, so it remains a modest contribution.

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?

A single front-loaded sentence with zero filler; the live scope comes first and the field list follows compactly. Nothing is repeated and every clause carries information.

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 two-parameter, zero-required, read-only list tool with no output schema, the description adequately conveys what comes back and roughly how to think about the family filter. The main omission is anything about result size or ordering, plus the handles filter's purpose, which the schema partially covers.

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%, so the baseline is 3. The description's parenthetical 'with its family: claude, openai, gemini...' does illustrate what the family filter means, but the handles parameter (builder handles) is never touched on in the description, leaving no added semantics there.

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 specific resource and scope — agents currently broadcasting live — and enumerates the fields returned (goal, kind, tags, agent/family, step count, latest step). It is clearly a live-discovery listing, distinguishable in substance from siblings like my_broadcasts or search_runs. It stops short of naming those siblings explicitly, so it is clear but not fully differentiated.

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?

There is no explicit when-to-use guidance and no mention of alternatives such as watch_stream, my_broadcasts, or search_runs. 'Right now' hints at a live-snapshot use case, but the agent must infer both the trigger and the boundary against the many sibling tools.

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