update_device

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

The description goes beyond the annotations by disclosing the merge-not-replace semantics for custom_properties, which is a high-value behavioral nuance not present in the schema or annotations. It also adds an authentication/authorization precondition ('requires write permission'). This is consistent with readOnlyHint=false, destructiveHint=false, and openWorldHint=true. Slightly short of a 5 because it does not clarify whether other list fields like host_group_ids are replaced wholesale or merged.

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 with zero filler: the first states the action and the permission prerequisite, the second captures the most operationally important nuance (merge semantics). Each sentence earns its place and the critical behavioral detail is front-loaded immediately after the purpose.

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 7-parameter mutation tool with no output schema, the description covers the purpose, the permission requirement, and the trickiest behavioral nuance. With no output schema, the return value is left undisclosed, but this is a minor gap for an update operation. The rich input schema and annotations carry the remaining burden, making this definition largely complete.

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 100%, setting a baseline of 3. The description adds genuine parameter-level meaning by specifying merge behavior for custom_properties, which materially changes how an agent sets that argument. Other parameters are already well described in the schema, and the description does not need to repeat them. The additive merge insight raises it above baseline.

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: 'Update an existing device/resource.' The word 'existing' adds a scope qualifier that distinguishes it from create_device, and the resource name separates it from update_device_instance, update_device_property, and update_device_group. It falls short of a 5 because 'device/resource' is slightly imprecise and it does not explicitly name a distinguishing sibling.

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?

No guidance is given on when to use this tool versus the many related siblings (get_device, create_device, delete_device, recover_device, update_device_instance, update_device_property). The 'requires write permission' note is a prerequisite, not a routing guide, and there are no exclusions, conditions, or alternative-recommendations. An agent must infer the boundary between this and similar device-scoped mutating tools.

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