Submit Sandbox Guardrail Evidence

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

Annotations provide basic traits (readOnlyHint=false, openWorldHint=true). Description adds context of simulator usage but no additional behavioral info beyond annotations.

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 sentences, front-loaded with purpose and exclusion, no extraneous information.

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?

With 8 parameters, low schema coverage, and minimal description, the tool definition is incomplete for correct invocation despite output schema existence.

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 coverage is low (38%) and description does not explain any parameter beyond the general 'evidence' concept, failing to add meaning.

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 verb 'submit' and resource 'evidence' for sandbox guardrail intents, distinguishing from sibling paybond_submit_spend_evidence.

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?

Explicitly states when to use (sandbox guardrail) and when not (live Harbor spend), naming alternative tool paybond_submit_spend_evidence.

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