game_screenshot

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

With readOnlyHint already declaring the safety profile, the description adds real value by disclosing the return format (PNG image) and, critically, that no control refs are created — a side-effect distinction from related tools. It stops short of saying whether the image is live or cached, or what it covers.

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?

Two short sentences with the purpose front-loaded and the exclusion second. Every clause carries information; nothing is redundant padding.

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 zero-parameter, annotation-covered tool with no output schema, the description supplies what matters: the output is a PNG and no refs are registered. Minor gaps remain around image freshness and scope, but nothing needed to invoke it correctly is missing.

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 tool takes no parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The prose correctly implies a parameterless call rather than hinting at hidden arguments.

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?

States a specific verb and resource ('Read a PNG of the game') and adds a negative scope marker ('Does not create control refs') that separates it from game_snapshot. It never names the sibling outright, so the differentiation is inferred rather than explicit.

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?

Gives two concrete situations for use: interpreting icon-only controls and visually verifying a ticket. There is no explicit 'do not use when' or named alternative, but the negated capability clause steers an agent toward game_snapshot for ref-producing work.

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