create_agent_run

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

Annotations are minimal (readOnlyHint=false, etc.), so the description carries the burden. It discloses that the run is persisted, audit-logged, and has a step log, events, and a replayable checkpoint. It explains the lifecycle states (completed, requires_approval, paused) and how they are triggered. No contradiction with annotations; it actually reinforces that it's a write operation.

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 detailed but well-structured. It opens with the core purpose, then explains modes, then persistence and audit, then alternatives, and finally return value. No fluff; every sentence adds value. It's a bit long, but for a complex lifecycle tool, it's appropriate, so 4 rather than 5.

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 tool with 7 parameters, nested objects, and no output schema, the description covers the essential behavior: what it does, how modes affect execution, what gets persisted, and what is returned. It also references related tools. It's sufficient for an agent to call it correctly.

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 schema already has 100% description coverage for all parameters, so the baseline is 3. The description adds context beyond the schema by explaining the behavioral impact of approval_mode and start_paused (e.g., parks at requires_approval or paused). It also mentions the return value includes run_id and status, which is not in schema. This enriches parameter understanding, so a 4 is warranted.

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 the tool's purpose: to create a persisted agent run lifecycle resource. It distinguishes itself from siblings by mentioning approval_mode and start_paused, and explicitly names alternative tools for different use cases. The verb 'create' and resource 'agent run' are specific and 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?

It explicitly says when to use this tool vs alternatives: 'Use product_agent_run for the simpler synchronous helper, list_agent_runs to browse, and get_agent_run_events to follow the trail.' It also explains the behavioral differences between auto and manual approval modes and start_paused, giving clear guidance on when this tool is appropriate.

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