dosbox_read_framebuffer

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

The description goes far beyond the readOnlyHint by explaining that a reference page is required for confirmation, that a blind scan otherwise occurs but is refused, that confirmed locations are cached, and that the tool writes <stem>.bin and <stem>.png when a stem is provided. These are consequential observable behaviors an agent needs to know.

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 paragraphs, each with a distinct job: what it is, the reference/caching constraint, and the outputs/page-flip behavior. It is longer than the minimal examples but stays dense and front-loaded; the all-caps phrase is loud but not actually redundant.

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 6-parameter tool with no required arguments, this description supplies the essential decision context: when to use it, what the reference requirement is, why the cache exists, what files are written, and how page_offset relates to page-flipping. With the output schema present, the return values need not be re-explained.

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 high (83%), so the schema does much of the work. The description adds meaningful semantics to reference (64,000-byte frame, byte-for-byte confirmation), stem (writes .bin/.png), page_offset (page-flipping games), and allow_unconfirmed (takes the unsafe blind scan). It does not add nuance for pid or expose the 'relocate' parameter by name, though schema descriptions cover those.

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 opens with a specific, purposeful verb and resource: "Read the guest's screen straight out of the emulator's video memory." It then precisely characterizes the return (palette indices at the instant of the read) and calls out the sibling it is not, dosbox_capture_screen, making the tool unambiguous.

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: 'Prefer this over dosbox_capture_screen for anything quantitative,' with reasoning about guest-time cost and half-drawn frames. It also states the reference requirement, the refusal to guess by default, and when allow_unconfirmed is appropriate.

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