show_headless_desktop

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

Beyond annotations, the description reveals key behaviors: it is temporary, the off-screen desktop becomes interactive and visible, there is a topmost non-dismissible banner with an EMERGENCY EXIT button that restores the normal desktop. It also discloses the return JSON fields. No contradiction with annotations; annotations indicate mutation (readOnlyHint=false) and non-destructive behavior, which align with the description.

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 well-structured with separate paragraphs for purpose, behavior, arguments, and returns. Each sentence adds meaningful detail. It is a bit longer than strictly necessary, but no part is wasted, and the use of sections makes it easy to scan.

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 tool's core behavior, return format, and companion tool. It does not mention prerequisites (e.g., whether a headless desktop must already exist) or the confirm_focus_disruption parameter, but given the output schema is present and the description is otherwise thorough, it is sufficiently complete for a moderately complex tool.

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 mentions 'desktop name and banner instruction,' which maps to the 'name' and 'instruction' properties, but it omits 'confirm_focus_disruption.' Although the schema provides detailed descriptions for each nested property, the context signal indicates 0% schema description coverage at the top level, placing a burden on the description to compensate. The description only partially covers the parameters, missing a critical confirmation flag.

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's purpose: 'Temporarily switch the live screen to a headless desktop for human interaction.' It uses a specific verb and resource, and distinguishes itself from siblings by describing the interactive handoff scenario and referencing the companion tool hide_headless_desktop.

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 explicitly states when to use it: 'so a person can complete a LOGIN or any manual step.' It also provides an explicit alternative/next step: 'Call hide_headless_desktop to switch back normally afterwards.' This gives clear usage context and differentiates from related tools.

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