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

Annotations already declare idempotentHint=true, readOnlyHint=false, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds substantial behavior beyond that: it retains screening evidence according to policy, may create a review case, and consumes sandbox allowance rather than paid production allowance, plus the retry semantics of the idempotency key. These are exactly the side effects an agent needs to anticipate.

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?

Five dense sentences, front-loaded with the core action before constraints and side effects. Every sentence contributes, though 'sandbox@1' is opaque enough to cost a little clarity.

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 nested, complex submission tool with an output schema present, the description covers quota, retention side effects, review-case creation, and idempotency reuse. The main gap is the unexplained nested request payload, but the schema and output schema carry that detail.

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 carry the load. It documents synthetic=true and the idempotencyKey format/length/reuse semantics well, and 'cannot link counterparties' implicitly addresses counterpartyId. However, the three-parameter nested `request` object (policy, subject, identifiers, retention, reference) is not explained at all, leaving a large share of parameters undocumented in both places.

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?

States a specific verb (Submit) and resource (invented data to sandbox@1), and the title/description make clear this is a sandbox screening test. An agent can distinguish it from validate_screening_request, get_screening_result, and get_screening_result-style siblings without opening the schema.

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?

Gives explicit constraints and exclusions: 'Requires synthetic=true', 'Cannot screen production or link counterparties'. These tell the agent when the tool is not appropriate. It stops short of naming the alternative sibling (e.g., validate_screening_request) for the invalid cases, so it is clear context rather than full routing guidance.

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