computer

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

The description discloses several non-obvious behaviors beyond the annotations: screenshots are downscaled and coordinates are mapped back, screenshots wait for the screen to stabilize, non-ASCII text is pasted via a clipboard that is restored, and non-screenshot/zoom actions return a confirmation rather than an image. These details substantially enrich the openWorldHint and destructiveHint annotations without contradicting them.

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?

Four short sentences, each carrying one distinct fact: scope, coordinate system, screenshot/clipboard behavior, and output format. The most important scope statement is front-loaded, and there is no filler or repeated schema content.

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 12-parameter, 13-action GUI tool with no output schema, the description covers the essential non-schema semantics: coordinate space, output behavior, clipboard side effect, and screenshot timing. Combined with the detailed schema and annotations, an agent has enough information to invoke actions and interpret results correctly.

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 description adds important meaning beyond the schema, especially the coordinate mapping from downscaled screenshots and the clipboard-based handling of non-ASCII text. Since schema description coverage is already high at 83%, the description does not need to repeat every parameter, but it adds the key behavioral context that makes coordinate and text parameters safer to use.

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 identifies the resource scope: 'Mouse, keyboard and screen on the user's GNOME desktop.' This distinguishes it from perception-oriented siblings like read_screen and ocr. However, it lacks an explicit verb such as 'control' or 'operate', so it is clear by implication rather than through a direct action statement.

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 scope line implies this is the GUI interaction tool, and the closing advice to 'take a screenshot when you need to see the outcome' gives workflow guidance. However, it never names sibling tools or conditions for choosing computer over read_screen, form_input, or computer_batch, so the usage guidance is only implied, not explicit.

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