update_device

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

Annotations already declare readOnlyHint=false and destructiveHint=true, but the description adds substantial behavioral context: it captures prior values of changed keys to record an undo and a faithful audit trail, labels itself [WRITE][risk=medium], and offers a dry_run preview. This goes well beyond what the structured annotations convey.

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 front-loaded with [WRITE][risk=medium] and the core operation, then layers in behavioral and parameter details without waste. The Args section is justified because the schema itself has no field descriptions.

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 non-idempotent, destructive write tool with a nested attrs object, no output schema, and zero schema description coverage, the description supplies the missing pieces: safety framing, preview path, undo/audit behavior, and all four parameter meanings. Nothing an agent needs to invoke it correctly is missing.

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%, so the description must compensate, and it does: it documents serial, attrs with an explicit list of allowed keys (name, tags, address, notes, lat, lng, floorPlanId), dry_run's preview behavior, and target's default behavior. This meaningfully compensates for the undocumented nested object.

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 device attributes (name/tags/address/notes).' It is clearly a mutation tool for device attributes, distinct in kind from siblings like reboot_device or device_status, but it never names a sibling alternative to sharpen the boundary.

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?

Usage is implied by the verb and framing, and it does mention 'Pass dry_run=True to preview,' which is operational guidance. However, it never says when to choose this over related siblings such as undo_apply or other update tools, so the guidance remains implicit rather than explicit.

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