list_devices

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

Annotations are absent, so the description carries the full burden for behavioral disclosure. It explicitly states that local keys are never returned, which is a security-relevant behavior important for the agent to know. It also mentions the return fields (names, device ids, IPs, protocol versions), but does not mention potential side effects (none likely) or performance implications. Given it is a read-only list operation, this is adequate.

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 brief (three sentences) and front-loaded with the main purpose. It immediately states what the tool does, then describes the output, and ends with a practical tip for using the results. Every sentence 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?

Given the tool has no parameters and an output schema, the description covers all essential aspects: what it lists, what fields are returned, and a crucial privacy note (local keys never returned). It is complete for an agent to invoke correctly without further information.

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?

There are zero parameters, and the schema has no properties, so the description has all the responsibility. It does not need to explain parameters, but it does describe the output content, which is a substitute. Since there are no parameters, the description is sufficient, and the baseline of 4 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?

The description clearly states what the tool does: 'List every Tuya device in the local registry.' It specifies the resource (devices) and the scope (local registry), and it is distinct from siblings like discover_devices, which likely handles network discovery rather than listing an existing registry.

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 clear context for when to use the tool: listing devices from the local registry, and it notes that the returned 'name' field is used when calling other tools, which implicitly suggests this is a prerequisite for other operations. It doesn't explicitly contrast with discover_devices but the mention of 'local registry' vs 'discover' implies the distinction.

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