shelly_script_eval

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

Annotations already declare destructiveHint:true, and the description adds value by noting that the result is stringified and operations are audit-logged. This provides additional context beyond the annotation, though it does not contradict it.

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?

The description is extremely concise with two sentences that convey the core purpose, a critical warning, and key behaviors. Every word serves a purpose with no redundancy.

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?

Despite having an output schema, the description omits crucial details: the meaning of 'device' and 'id', the fact that the script must be already running, and the shape of the returned object. Significant gaps remain given the parameter count and schema coverage.

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?

With 0% schema description coverage, the description must explain all parameters. It only clarifies 'code' (the expression) and 'confirm' (needed for arbitrary code), but leaves 'device' and 'id' completely unexplained. This is insufficient for proper usage.

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 clearly states the verb ('Evaluate') and the resource ('expression inside a running script'), and implies the context of a Shelly device. It also highlights a key differentiator (arbitrary code needing confirm:true), which helps distinguish from other script tools like shelly_script_get_code or shelly_rpc.

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 description provides a specific guideline about using confirm:true for arbitrary code, but lacks explicit when-to-use vs alternatives, prerequisites (e.g., script must be running), or when-not-to-use. The guidance is present but incomplete.

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