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

No annotations are supplied, so the description carries the full burden. It does disclose the key trait — that this mutates order state to 'installed and used' and thereby feeds refund and dispute rules — but says nothing about whether the simulation can be undone, what authorization is required (agent_key/principal_id are in the schema but unexplained), or what result is returned.

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 short sentences with zero waste; the sandbox restriction is front-loaded and the behavioral effect follows immediately.

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 5-parameter mutation tool with no annotations and no output schema, the description covers purpose, scope restriction, and downstream effect adequately. The remaining gap — reversibility and required credentials — is modest but real.

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 every parameter, including the 120 MB default, is already documented in the schema. The description adds nothing about order_id selection or how data_used_mb affects eligibility outcomes beyond what the schema states, so the 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?

It states a specific verb and resource: 'Marks the order's eSIM as installed and used, as if the traveler activated it.' The 'Sandbox only' prefix distinguishes it from the real activation path (regenerate_activation), and the simulated state change is described precisely enough that an agent knows exactly what will happen.

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?

'Sandbox only' is an explicit exclusion, and 'Use it to exercise refund and dispute rules' gives a concrete when-to-use scenario. What's missing is an explicit alternative for real (non-sandbox) activation, though the sibling regenerate_activation is implied.

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