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

Annotations already declare readOnlyHint=true and idempotentHint=true, lowering the burden on the description. The description adds valuable sandbox behavior by noting that sandbox proof is explicitly marked simulated, which an agent would not know from annotations alone.

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 with no filler: the first states the core action and resource, and the second adds a relevant sandbox caveat. Every sentence earns its place.

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 simple read-only retrieval with one required, schema-constrained parameter, the description and annotations are mostly complete. It does not describe failure behavior or the exact response shape, but 'retrieve the completion proof' adequately conveys the return concept for this simple tool.

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%, and the description says nothing about delivery_id or robomart_version. The agent must infer the meaning of the delivery identifier from its name and the version parameter from its const value; the description does not compensate for the missing schema descriptions.

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 names a specific resource ('completion proof') and a specific action ('Retrieve'), and scopes it to 'a delivered job.' This clearly distinguishes it from sibling tools like book_delivery, cancel_delivery, check_coverage, and track_delivery.

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 phrase 'for a delivered job' implies the tool is appropriate only after a delivery has occurred, which supplies clear contextual guidance. However, it does not explicitly state when not to use it or name alternative tools for other delivery-related tasks.

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