job_dashboard

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

Beyond the annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false), the description reveals that the dashboard long-polls job_watch, that updates do not create model turns, and that job history is not exposed. This is valuable behavioral context not present in the structured annotations.

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 short sentences, each carrying non-redundant information: core function, parameter behavior, and polling transparency. The content is front-loaded and every sentence earns its place.

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 tool with one optional parameter, no output schema, and strong annotations, the description is complete. It covers the primary function, the parameter's conditional behavior, and the key side-effect of not generating model turns or exposing history—enough for an agent to select and invoke 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?

The description greatly enriches the meaning of the single optional parameter: providing jobId reopens a known task, while omitting it selects the newest non-terminal task. The schema only states 'Tracked task to display without showing other jobs,' so the description adds concrete selection behavior.

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 opens with 'Render one live RunBeacon task,' naming a specific verb and resource. The subsequent sentence clarifies behavior with and without jobId, and the mention of long-polling job_watch distinguishes it from sibling tools like job_list or job_watch.

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 conditional guidance for the optional jobId ('Pass jobId to reopen a known task; without it, the newest non-terminal task is selected'). It also implies a UI-level use case by referencing job_watch, but it does not explicitly name alternative tools or state when not to use the dashboard.

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