block_device

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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false and closed-world scope, so the safety profile is partly covered. The description's only addition is 'Two-phase', which hints at a confirm protocol but never explains what each phase does, whether the first call is a no-op, or how expected_etag guards against races. For a mutation tool that omits those mechanics, the value added is thin.

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 text is short and front-loaded with the action, with no filler words. However, the brevity crosses into under-specification: the single most important behavior, the two-phase protocol, is compressed into two words rather than explained.

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?

An output schema exists, so return values need no prose. Still, for a state-changing, three-parameter tool with zero schema description coverage, the definition omits the confirm/etag workflow that an agent needs to invoke it correctly, which is a material completeness gap.

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 carry all parameter meaning; it clarifies only 'mac'. The two parameters that drive the advertised two-phase workflow, confirm and expected_etag, get no explanation anywhere, leaving the agent to guess their roles and the correct call sequence.

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?

States a specific verb and resource ('Block a device'), the identifying parameter ('by MAC'), and the effect scope ('from the network'), which distinguishes it cleanly from unblock_device and list_blocked_devices. It stops short of naming the sibling it pairs with, but the purpose is unambiguous.

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?

'Two-phase' is the only usage signal, and it is never unpacked: the agent is not told that a first call previews and a second call with confirm=true commits, nor when to prefer this over unblock_device or check list_blocked_devices first. No prerequisites or failure conditions are given.

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