start_run

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

With no annotations, the description fully bears the transparency burden. It clearly states the tool returns immediately with a task id and runs in the background. It doesn't disclose cancellation, error handling, or resource limits, but the core async behavior is well communicated.

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 very concise: two sentences plus a recommendation, all front-loaded with the core action. Every sentence adds value with no redundancy or fluff.

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?

Given the complexity (11 parameters, many optional) and presence of an output schema, the description explains the output (task id) and how to use it with siblings. It doesn't detail the output schema structure, but the core flow is covered. It adequately addresses the tool's role among 11 siblings.

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 low (18%), so the description should compensate. It mentions tool, prompt, repo_root as parameters implicitly but does not elaborate on all 11 parameters. The description adds context for usage but doesn't map to individual parameters beyond the overall flow.

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 explicitly states the action: 'Start a Dobby tool in the background and return immediately with a task id.' It clearly distinguishes from sibling tools like wait_run, get_run, and list_runs by explaining the asynchronous behavior and follow-up patterns.

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?

Provides explicit when-to-use guidance (short timeouts), follow-up patterns (wait_run with single or multiple task_ids), and alternatives (get_run/list_runs for non-blocking peek). This gives the agent clear decision criteria.

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