dosbox_capabilities

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

Though the readOnlyHint annotation already signals a safe read operation, the description adds meaningful behavioral detail beyond that: it openly discloses specific host limitations (window capture and emulator menu commands are unavailable) and frames/recordings dependency caveats. This is useful context an agent cannot infer from structured fields alone.

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 two sentences, front-loaded with the core purpose, then specific constraints, and then usage triggers. Every sentence carries information and there is no fluff or 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?

With zero parameters, an output schema present, and readOnlyHint true, the description covers everything an agent needs: what this tool provides, what it does not provide, and when to invoke it. There are no missing contextual details that would prevent correct selection or invocation.

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 zero parameters and schema coverage is trivially 100%, so the baseline for this dimension is 4. The description adds context about the tool's purpose without discussing parameters, but none are needed. It does not compensate for absent parameters; it doesn't need to.

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 purpose: enumerating host capabilities and limitations, with concrete examples ('Guest memory works everywhere there is a backend; window capture and the emulator's own menu commands do not'). It is clearly distinct from the sibling tools, which are actionable operations (launch, capture, read memory, etc.) rather than a capabilities overview.

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?

Explicit usage guidance is provided: 'Call this when a tool refuses, or before planning a session that depends on frames or recordings.' This directly tells the agent when the tool should be consulted, which is exactly the kind of contextual advice the rubric rewards.

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