create_decision

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

No annotations are provided, so the description carries the burden. It discloses that the tool both creates and verifies, and returns several artifacts, but does not detail side effects, permissions needed, or what verification entails beyond returning data.

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 a single, information-dense sentence that front-loads the action and outcome, listing key return values. No wasted words.

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 schema fully documents parameters and the description enumerates meaningful return values, the tool is adequately described for an agent to select and invoke it. It lacks explicit guidance on prerequisites or failure modes but remains complete enough for straightforward usage.

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 100%, so the schema already documents all parameters. The description adds the purpose of the tool (creating a decision) and example output fields, complementing the schema without needing to repeat parameter details.

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 states a specific verb ('Create and verify') and resource ('decision via the Trust OS Decision API'), and lists concrete outputs. It distinguishes clearly from the sibling 'verify_decision' by emphasizing creation and returning identifiers like decision_id and trace_url.

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 description implies this tool is for creating a decision, but it does not explicitly state when to use it versus the sibling 'verify_decision'. It provides context about verifying via the API but lacks clear alternatives or exclusions.

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