Get a structured Harness run summary

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds the useful notion of a 'durable snapshot' projected into 'stable' fields, implying a consistent contract across polls, but it says nothing about behavior for unknown/expired runIds or how staleness is handled.

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?

One sentence, front-loaded, with no filler. Slightly abstract phrasing ('project the current durable run snapshot into') is the only cost, and the field list makes up for it.

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?

An output schema exists so return shape needn't be described, and annotations carry the safety profile, leaving the description adequate. But for a tool sitting in a dense cluster of run-inspection siblings, the missing disambiguation is a real gap for correct tool selection.

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 0%, but there is only one parameter and it is fully self-describing as a UUID with an explicit pattern, including the nil and all-ones sentinels. The description adds no meaning about where runId comes from or what a nil/ffffffff id would resolve to.

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 action (projecting a snapshot) and enumerates the exact fields produced (status, model, permission, elapsed time, next-action), which tells the agent what it will get back. It does not, however, distinguish itself from close siblings like get_run, status_run, or wait_run, so an agent still has to guess which of the four it wants.

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 guidance on when to call this versus get_run, status_run, or wait_run, and no mention of whether the run must be active, completed, or owned by the caller. The single hint is 'current durable run snapshot', which implies read-only inspection but not a selection rule.

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