Read raw bytes from Game Boy memory at a hexadecimal address, optionally specifying length, to inspect emulator state beyond decoded values.
Read raw bytes from Game Boy memory (hex address like 'D35E'). Escape hatch for the curious.
| Name | Required | Description | Default |
|---|---|---|---|
| length | No | ||
| address | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. 'Read' plus 'escape hatch' signals a non-mutating, low-level/power-user operation, which is useful framing, but there is no disclosure of legitimate address ranges, what happens on an invalid address, byte ordering, or any permission/risk caveats. Return shape is covered by the output schema, so that omission is acceptable.
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 no filler, and the address format — the most call-critical detail — is front-loaded. The second sentence does double duty as usage guidance rather than being waste.
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 only two parameters, an output schema covering results, and no annotations, the description is nearly serviceable, but it omits the length parameter's meaning and any notion of valid address space or error behavior — details an agent needs to call this raw-memory tool reliably.
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 0%, so the description must compensate. It genuinely adds value for 'address' by specifying hexadecimal format with an example, but the 'length' parameter (default 1) is never mentioned, leaving half the parameters undocumented in both schema and description.
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 raw bytes from Game Boy memory') and gives a concrete address format example ('D35E'), so the agent knows exactly what operation this is. The 'escape hatch for the curious' framing implicitly separates it from the structured sibling read_game_state, though it never names that sibling.
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?
'Escape hatch for the curious' hints that this is a low-level fallback for when structured tools are insufficient, but it never says so explicitly or names the alternative (read_game_state) the agent should normally prefer. The guidance is implied rather than actionable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.