Handy Permission Control (On/Off Toggle)

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

Beyond the annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false), the description discloses the actual side effects of toggling off — screen capture and input control are disabled immediately and held inputs are released. It also discloses the asymmetry that re-enabling is blocked unless an environment flag is set, which is exactly the kind of auth/reversal context annotations cannot 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?

Three sentences, front-loaded with the core capability, then consequences, then the re-enable constraint — no filler. Minor cost: the 'Inspect or turn OFF' framing in sentence one is not reconciled with the 'on' action listed in the schema, forcing a second read.

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 small, annotation-covered toggle with no output schema, this is nearly complete: effects, reversal path, and the env-var gate are all present. The remaining gap is that the 'status' path returns something undocumented (despite no output schema), and the description never states what state information the agent will get back.

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?

With 100% schema description coverage on both enum parameters, the baseline is satisfied without the description. The description does add real meaning for `action: 'off'` (immediate disable plus input release) and gives the precondition for 'on', but it adds nothing about the `mode` parameter (full vs view_only) beyond the one-word schema text.

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 pairs specific verbs with a specific resource ('inspect or turn OFF Handy computer control permissions') and names the concrete effects of the off path (screen capture, mouse/keyboard control, releasing held inputs). It is slightly muddled because the opening sentence frames the tool as inspect/off only while the schema also exposes an 'on' action discussed later in the text, so an agent must read the whole description to learn the full capability set.

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 gives clear operational context: use it to inspect state or to immediately disable Handy, and it warns that re-enabling requires an out-of-band command unless HANDY_ALLOW_MCP_ENABLE=true. It does not differentiate from siblings such as handy_status (whose territory the 'status' action overlaps) or state when to prefer one over the other, so routing is left to inference.

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