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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is known. The description adds real behavioral context beyond that: 'Answers already in stay' tells the agent partial results are preserved and 'May return needs_confirmation' warns of a confirmation envelope. It omits what happens if the run is already terminal or whether cancellation is reversible, keeping it short of a 5.

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 terse sentences, front-loaded with the action and affected states before the preservation note and the return caveat. Every clause carries information; no filler.

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 destructive mutation with no output schema, the description covers the target states, the side effect on existing answers, and the confirmation-envelope return path that maps to approvalId. Remaining gaps (terminal-state behavior, irreversibility) are minor against annotations that already flag destructiveness.

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 67%; workspace and approvalId are described in the schema, and runId is self-evident. The description usefully links the needs_confirmation return to the approvalId parameter, adding meaning the schema alone does not, but it adds nothing for runId or workspace, so baseline-range credit is appropriate.

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?

States a specific verb (Stops) and resource (panel run) plus the eligible states (queued, running, paused), so an agent can distinguish it from prism_panel_runs_get and prism_panel_runs_estimate. It stops short of naming siblings explicitly, but the action and scope are unambiguous.

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 enumeration of valid states ('queued, running or paused') implicitly tells the agent when the call applies, and the needs_confirmation mention hints at a follow-up flow. However, there is no explicit when-not guidance, no mention of alternatives, and no prerequisites (e.g., permissions) beyond what the schema carries.

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