computer.observe

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

With no annotations, the description fully carries the burden of behavioral disclosure. It transparently describes what the tool returns, including the available levels and their composition ('normal' = screenshot+OCR+accessibility, 'full' adds focused element details). It does not mention potential side effects, but the read-only nature of observing is evident from the verb and examples.

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?

Three concise, information-dense sentences: the first states the tool's scope, the second defines the parameter levels, and the third frames its role relative to other actions. No wasted words; all content serves the agent's decision-making.

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?

Given no output schema and no annotations, the description does a solid job covering what the tool does, the parameter options, and when to use it. It does not describe the return format or potential limitations (e.g., accessibility API failing), but for an observe tool the listed components give sufficient context for an agent to invoke it and understand the result.

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 only parameter, 'level', has no schema description and no enums, yet the description fully documents the three valid values and what each returns: 'minimal' (fast), 'normal' (screenshot+OCR+accessibility), and 'full' (adds focused element details). This completely compensates for the 0% schema coverage.

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 verb ('Observe') with a clear resource ('current computer state') and enumerates exactly what is included: screen geometry, active window, cursor, OCR'd text, and accessibility elements. It also distinguishes itself from sibling tools by explicitly calling itself the 'primary tool for understanding the screen before acting,' which sets it apart from specific helpers like screenshot or get_active_window.

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 actionable usage guidance by stating this is the primary tool to use before acting on the screen. It does not explicitly list when to prefer alternatives like computer.screenshot or computer.get_ui_tree, but it implies a general-purpose role that precedes-specific actions. The 'fast' minimal level also suggests a use case when speed is needed.

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