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

Annotations already establish read-only, idempotent, non-destructive behavior, so the description sensibly spends its words on non-obvious data semantics instead: seeds are per-organisation, one per scenario, and the signature_mismatch entry carries a deliberately WRONG signature while not_found is a UID absent from the register. That prevents an agent from misreading intentional test fixtures as errors. It stops short of describing return shape beyond the scenario list.

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, zero waste: the first defines the output and enumerates the scenarios, the second carries the sandbox constraint and the use case. The most important qualifier ('Sandbox only') is placed where it cannot be missed.

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 no parameters and no output schema, the description carries the full explanatory burden and does so: it enumerates every scenario returned and clarifies the intent of the anomalous entries. An agent has everything needed to call it and interpret the result.

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?

The tool takes zero parameters, so the schema cannot carry semantic load and the baseline is 4. The description does add meaning to what is returned (UID plus signature, one entry per named scenario), which is the only semantic detail available for a no-arg call.

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 and resource ('List the seeded sandbox chips') plus the exact payload returned: UID and signature to pass to verify_chip. It names the four scenarios returned, so an agent can distinguish this from production-oriented siblings like verify_chip or list_shipments 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?

Explicitly scopes usage: 'Sandbox only — use when building or testing an integration before physical chips ship.' It also routes the agent downstream by naming verify_chip as the consumer of the returned UID/signature. When-to-use and the boundary against real-chip flows are both stated.

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