shelly_script_eval

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

Despite destructiveHint=true being annotated, the description adds meaningful context: the confirmation gate for arbitrary code, the 'stringified result' return shape, and that the operation is audit-logged. These go beyond the annotation and inform the agent about safety and side-effect visibility.

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 tight sentences with the core action and the confirm-gating rule front-loaded; nothing is wasted and the critical safety note is prominent.

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?

An output schema exists, so return values needn't be elaborated, and the description covers the confirmation gate and logging. But with 0% parameter documentation and an undescribed device/id targeting scheme, the definition is not fully complete for a destructive 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% across 4 parameters, so the description carries the burden. It only clarifies the `confirm` flag (and implicitly `code` as an expression); the `device` and `id` parameters are left completely unexplained in both description and schema.

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 and resource ('Evaluate an expression inside a running script'), which distinguishes it from siblings like shelly_script_put_code or shelly_script_get_code. It is clear what the tool does, though it does not explicitly name the alternatives it is not.

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?

It provides one actionable rule — arbitrary code requires ``confirm:true`` — which is genuinely useful. However, it gives no guidance on when to prefer this over shelly_rpc/shelly_rpc_write or other siblings, leaving selection context implied.

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