Get run

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

Annotations already declare readOnly/idempotent, so the lower bar applies; the description still adds real behavioral context by disclosing what each mode returns (step status/durations/IO vs state/step history/output/error) and the awaitingEvents field feeding control_run. Lacks any note on size limits or latency for deep step histories, keeping it below 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?

Four dense sentences, each covering a distinct decision point (executionId mode, instanceId mode, mutual exclusion, simple flag), front-loaded with the core purpose. 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?

With an output schema present, the description needn't enumerate return shapes, and it still characterizes the content per mode plus the awaitingEvents linkage. Everything an agent needs to choose a mode and call correctly is present.

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 100%, yet the description adds the crucial non-schema constraint that executionId and instanceId are mutually exclusive one-of, and that simple is only meaningful with instanceId. That is semantics the schema alone does not enforce or convey.

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+resource ('Get one run's details') and immediately splits into the two distinct run flavors (executionId execution logs vs instanceId durable runs), making it distinguishable from list_runs and get_deployment_status. An agent knows exactly what it retrieves.

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?

Explicitly states 'Pass exactly one of the two' and names where each id comes from (list_runs history / run_workflow or list_runs instances). It also names the downstream consumer (control_run send_event must use awaitingEvents) and when to set simple for cheap polling.

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