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

Beyond the annotations (readOnlyHint=false, idempotentHint=true), the description adds critical scope context: it only creates a manual-review request and does NOT automatically hire, pay, purchase, or promise fulfillment. This directly protects the agent from assuming commitment/payment side effects, which the annotations do not convey.

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?

Three tight sentences, front-loaded with the trigger condition and examples, and closed with the crucial limitation. Every sentence earns its place with no filler.

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 write/request tool with no output schema, the description covers purpose, examples, and the non-committal nature well. The main gap is silence on how it relates to the verification-request siblings, which is exactly the ambiguity an agent faces here.

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?

At 57% schema description coverage the schema documents the key fields (objective, idempotency_key, location, max_budget_jpy), but the description adds no parameter-level meaning of its own and offers nothing for deadline, constraints, or evidence_requirements. Baseline 3 for a schema that does most of the work.

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+resource — creating a manual-review request for external execution in Japan — and clarifies it is a request rather than fulfillment. However, it never differentiates itself from the sibling request tools (create_verification_request, prepare_verification_request), so an agent can't tell which request family to pick from the description alone.

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?

Strong when-to-use guidance: 'Use when an AI cannot complete a task itself and needs a human or provider in Japan,' reinforced with concrete examples (calling a business, photographing, shipping). It lacks any when-not or explicit alternative routing, which is notable given the overlapping verification request siblings.

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