Key

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

Annotations already flag destructiveHint=true and readOnly=false, so the description does not need to restate the safety profile. It adds the scoped-application targeting behavior, but it does not disclose potential side effects such as triggering application shortcuts or whether the target app must be focused.

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 a single sentence with no filler, and the action verb and target are front-loaded. Every word adds meaning, making it appropriately concise for the tool's basic purpose.

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 five-parameter tool with no output schema and many sibling input tools, the description is adequate but thin. It establishes the high-level action and target while relying on the schema for parameter details, but it lacks routing guidance and app_ref semantics, so an agent may need additional information to invoke it confidently.

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 already cover text, strategy, and return_state, with a basic description for repeat, while app_ref has no schema description. The description's 'scoped application' hints at the role of app_ref but does not specify its format, and no other parameters are elaborated.

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 action verb ('Send'), names the object ('a key or chord'), and specifies the target ('a scoped application'), so the core function is clear. It does not explicitly contrast with sibling tools like type or hold_key, but the scoped-application qualifier helps distinguish it from global input.

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?

The phrase 'to a scoped application' implies this is for app-targeted input, which is a useful usage signal. However, there is no explicit guidance on when to prefer key over type, hold_key, or perform_action, and no exclusions or prerequisites are stated.

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