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

Annotations already declare readOnlyHint=false, openWorldHint=true, and destructiveHint=true, so the safety profile is provided. The description adds the planner decomposition behavior and output piping, which is useful context beyond the annotations. However, it doesn't disclose what destructive side effects may occur, whether the job is immediately executed, or if any prerequisites (like credentials) are needed. It adds some value but not rich behavioral context.

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?

Two concise sentences with zero filler. The primary purpose is front-loaded, and the planner behavior is explained in the second sentence. No redundant details.

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?

The description covers the core purpose and the planner behavior, and an output schema exists (so return values may be documented). However, the optional parameters are undocumented, and there is no mention of constraints, required credentials, or how the planner handles failures. For a tool with four parameters and a potentially destructive operation, this is not fully complete, but it's adequate for the main action.

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%, so the description must compensate. It only implicitly explains the 'goal' parameter ('natural-language goal'), but leaves deadline, budget_usd, and webhook_url completely unexplained. The agent must rely on naming conventions alone, which is insufficient for parameters like budget_usd (units? currency?) and webhook_url (format? events?). Only one of four parameters is semantically addressed.

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?

Clear and specific: 'Create a multi-step job from a natural-language goal' states the exact verb and resource, and the added detail about the planner decomposing the goal into ordered actions distinguishes it from sibling lifecycle tools like cancel_job or resume_job. The purpose is 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?

There is no explicit guidance on when to use this tool versus its siblings (e.g., start_task, invoke_action). The description implies it is for creating a job, but doesn't state exclusions like 'use resume_job instead if you want to continue an existing job.' An agent cannot determine the best tool choice from this description alone.

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