List panes

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

With no annotations provided, the description carries the full transparency burden. It discloses the heuristic nature of the liveness indicator ('busy/idle/exited liveness heuristic') and notes that org metadata is optional ('any org metadata'), setting accurate expectations for data quality. However, it does not explicitly state that the operation is read-only and side-effect-free, though 'List' strongly implies it. The inclusion of streaming URIs is a valuable behavioral clue for downstream usage.

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 a single well-structured sentence that front-loads the core action ('List all panes') and then efficiently lists the included data categories. There is no fluff, and every clause adds useful information about scope or return fields. It is appropriately sized for a simple list tool with no parameters.

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 there is no output schema, the description thoroughly covers what the tool returns: status, activity (with heuristic caveat), org metadata, tab/window context, and resource URI. This is sufficient for an agent to understand the tool's output without needing an output schema. The absence of params and the simple list nature mean no additional context (e.g., pagination, sorting) is critical, but the return field enumeration is complete enough.

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 input schema has zero parameters, so there is nothing for the description to clarify. The baseline for 0 parameters is 4. The description omits parameter details because none exist, and instead focuses on output fields, which is appropriate. No deduction needed since the schema coverage is trivially 100%.

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 a specific action ('List all panes') and the resource scope ('across all windows/tabs of the running hyperpanes instance'). It also enumerates the returned fields (status, activity, org metadata, tab/window context, resource URI), which distinguishes it from sibling tools like read_pane (which reads a single pane) or focus_pane (which changes focus). This is a model of purpose clarity.

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 provides strong context for when to use this tool: when you need a complete inventory of panes with their current state and streaming URIs. It does not explicitly mention alternatives or exclusions, but the scope ('all') and the data fields make it clear this is the enumeration tool, and sibling names like read_pane imply single-pane access. Lacks an explicit 'use X instead' statement, so not a 5.

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