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

Annotations already cover idempotency and non-destructive mutation; the description adds useful behavioral context: the job is synthetic and asynchronous, does not touch real data, and returns via 202-then-poll. This goes beyond what annotations alone 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?

Two sentences, no redundancy, with the core action and purpose front-loaded. The pointer to get_sandbox_job 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 one-parameter tool with output schema and annotations, the description tells the agent what it does, why it exists, and the follow-up call. Nothing essential is missing.

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 100% and the single parameter's description explains the semantics (same key -> same jobId). The description references the idempotency-key pattern, aligning with the schema, but adds no additional parameter-level detail. Baseline 3 applies.

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 ('Start') and resource ('synthetic asynchronous sandbox job'), and clarifies it exercises the Idempotency-Key and 202-then-poll pattern. It distinguishes from sibling get_* tools by framing it as the write-path sandbox.

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?

Clearly implies when to use it – to practice/validate the write API's idempotency and polling behavior without real side effects. It explicitly instructs to poll with get_sandbox_job, but it doesn't spell out when not to use it or name alternatives for read operations (though siblings are all reads).

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