eda_sys_shortcut_key_unregister

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

With no annotations present, the description carries the full behavioral burden and does so well: it discloses the boolean return, the throw-on-standalone-script failure mode, the extension-only constraint, and the system-shortcut limitation. This goes beyond a bare operation statement and gives an agent reliable expectations for side effects and errors.

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 front-loaded with the signature and operation, then ordered remarks, constraints, errors, version, and return. Each line earns its place, though the bilingual redundancy ('反注册快捷键' plus the signature) and version note are slightly extra.

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 unregister operation with no output schema, the description covers return value, error behavior, scope, and constraints. The remaining gap is the exact shortcut-ID format, and there is no example, so an agent may still need external information to construct a valid id.

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?

The input schema only exposes generic args/windowId wrappers, but the description adds the meaningful `id: string` signature and says the ID must be concatenated according to a format. The exact concatenation format is not specified, so it does not fully compensate for the schema's opacity, but it adds substantive parameter meaning.

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 clearly states the operation ('sys_ShortcutKey.unregister(id: string) -> boolean', '反注册快捷键') and scopes it to unregistering extension shortcuts while explicitly excluding system shortcuts. It does not, however, name or contrast any sibling tool such as eda_sys_shortcut_key_unregister_shortcut_key, so an agent must infer the difference.

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 remarks give concrete when-to-use context: it can unregister other extensions' shortcuts and cannot unregister system shortcuts. It also warns that it is only valid in an extension context and throws in standalone scripts. It stops short of naming an alternative for system-shortcut unregistration, so it lacks explicit alternatives.

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