observe

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

Beyond readOnlyHint and openWorldHint annotations, the description details behavior (no mouse/keyboard, default image false, quality/max_width defaults, changed flag handling, target id validity).

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?

Concise and well-structured: front-loaded with purpose, each sentence adds necessary information, no redundancy.

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?

Comprehensive despite no output schema; covers return format, edge cases (changed=false, dirty null), and usage context effectively.

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?

Adds meaningful context to all parameters (e.g., when to set image=true, mark default, quality/max_width defaults, changed flag behavior) beyond the schema descriptions.

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 the current screen returning UIA targets and a text summary. It specifies it does not move mouse/keyboard, distinguishing it from action tools.

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?

Provides explicit guidance: prefer send_actions for multi-step UI, observe after meaningful steps, conditionally set image=true, and handle changed=false by not re-analyzing.

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