create_run

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

Annotations already convey that this is mutating, non-destructive, and non-idempotent. The description adds no additional behavioral context such as side effects, state changes, required permissions, or failure behavior; it just restates the action and inputs.

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?

A single front-loaded sentence states the action, resource, and both parameters with zero filler. Every word 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 two-parameter creation tool with an output schema, the basics are covered. Still, the description is thin on behavioral caveats and sibling routing, making it adequate but not fully self-sufficient in the context of the orchestration-tool family.

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?

With 0% schema description coverage, the description must carry parameter meaning, and it partially does: 'goal' is a high-level goal and 'spec_json' is an optional JSON spec. However, it gives no detail about the spec_json format, accepted fields, or constraints beyond being a JSON string.

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 names a specific action ('Create'), a specific resource ('orchestrator run'), and the input shape ('from a high-level goal and optional JSON spec'). It also distinguishes itself from lifecycle siblings like resume_run and checkpoint_run by emphasizing a new run.

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 phrase 'new orchestrator run' implies this is for starting fresh rather than resuming, but the description never explicitly says when to choose this over resume_run, checkpoint_run, or plan_goal. The usage context is clear but exclusions and alternatives are left to inference.

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