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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the bar is lower. The description adds useful behavioral context: the device must be owned by the calling agent and accessed via a linked vendor connection. It does not contradict the annotations.

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 no wasted words. The action and scope are front-loaded, and the parameter dependency is stated in the second sentence. The parenthetical error is a clarity issue, not a conciseness issue.

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 two-parameter read tool with an output schema and full annotations, the description covers the purpose, ownership scope, and the need for both IDs. It doesn't detail return values, but the output schema handles that. The connection_id provenance error prevents a perfect score.

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 descriptions cover both parameters at 100%, so baseline is 3. However, the description says 'Requires connection_id (from device.list) and device_id.' This attaches the provenance '(from device.list)' to connection_id, while the schema clearly states device_id comes from device.list and connection_id comes from '/connect/device/connections'. This misleading attribution subtracts value and could cause an agent to look in the wrong place.

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 uses a specific verb ('Read') and resource ('current state of one physical device'), and further scopes it to devices the calling agent owns via a linked vendor connection. This clearly distinguishes it from sibling tools like device.registry.command (write) and device.registry.list (list devices).

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?

Provides clear context: read the current state of an owned device and requires both connection_id and device_id, with device.list referenced for one ID. It does not explicitly name alternatives or state when not to use it, but the read vs. command/list distinction is inferable from the description and sibling names.

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