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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, and destructiveHint=false. The description adds substantial context beyond annotations: the ~5 second wait, the fresh:false fallback for slow/offline screens, the 2 MB threshold that returns latestFrameUrl only, the screen.edit permission requirement, and the fact that it sends a device command. This reconciles the non-read-only annotation with the statement that screen content does not change.

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 front-loaded with the core action, then organized into clear 'When to use', 'When NOT to use', 'What to know', and 'Parameters' sections. Every sentence adds distinct operational value with no repetition or filler.

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?

An output schema exists, so the description need not explain return values in detail, but it still covers the important edge cases (timeout, fresh flag, size limit, permission, id sourcing). For a screenshot tool with annotations and an output schema, this is complete enough for an agent to invoke 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?

Schema coverage is 100% and the schema only says 'Screen id.', but the description adds the expected scr_… format, the source (list_items kind screens), guidance to call once per screen for multiple screens, and the error behavior for an id outside the connection's reach. This significantly exceeds the baseline for a fully documented single parameter.

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 states a specific verb and resource ('Take a new screenshot of one screen and return it as an image') and distinguishes itself from siblings by naming set_screen_content and control_screens as setup tools and get_screen_status as the diagnostic alternative. An agent can tell exactly what this tool does and when it is the right choice.

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?

It gives explicit 'When to use' and 'When NOT to use' sections, names the alternative for learning why (get_screen_status), and warns against polling in a loop. This is as clear as usage guidance gets.

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