get_selected_text

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

Without annotations, the description discloses behavioral traits such as the dependency on the last used app and the recommended fallback to clipboard. It implies it is read-only and non-destructive, but could be more explicit about return type or permissions. Overall, it adds useful context beyond the schema.

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 three short sentences, each with a clear purpose: primary function, optimal usage context, and fallback instruction. No unnecessary words, and information is front-loaded.

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?

The description covers the main task, usage context, and alternative. It lacks details about the return format (e.g., string) but for a simple read tool with no output schema, it is fairly complete. It adequately serves an AI agent's needs.

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 has zero parameters, so the description is not required to explain them. The baseline for no parameters is 4, and the description does not need to add parameter info. It focuses on the tool's behavior, which is appropriate.

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 tool reads highlighted text from the desktop. It differentiates from sibling tools like get_clipboard by describing when to use each. The verb 'Read' and resource 'text the user currently has highlighted' are specific and 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?

The description provides explicit guidance on when to use this tool versus the alternative get_clipboard. It says to use get_clipboard if get_selected_text returns no selection. It also notes it works best when the selection is in the last used app, giving context for optimal use.

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