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

Annotations already declare idempotentHint=true and destructiveHint=false, but the description goes further by explaining what 'close' actually means: connected viewers keep watching and the view only ends when nobody is connected. That is real behavioral context beyond the structured hints, plus an explicit safety statement for the idle case.

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 short sentences, front-loaded with the action and the sibling reference, followed by the two facts an agent needs (partial-close semantics, idle safety). No filler.

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 single-parameter, no-output-schema close tool, the description covers the action, the linking opener tool, the nuanced effect on connected viewers, and safe invocation when nothing is open. Nothing material 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?

Only one parameter (udid) with 100% schema description coverage, so the schema already carries the semantics. The description adds nothing about the parameter, which is acceptable at this coverage level but earns no bonus.

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 ('Release this server's hold on the device's live view') and explicitly ties it to the sibling that creates that state (ios_vnc_open_hid). An agent can distinguish it from ios_release_hid, ios_vnc_open_hid, and other release tools without opening a schema.

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?

Names the condition under which the tool applies (a live view opened by ios_vnc_open_hid) and adds a safety note for the no-op case. It doesn't enumerate when-not-to-use beyond that, but the parenthetical opener reference gives clear context.

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