mgba_read_memory

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

No annotations are provided, so the description carries full burden. It mentions running frames before reading, which adds some behavioral context, but fails to disclose critical traits: whether this is a read-only operation, what permissions or prerequisites are needed (e.g., ROM file access), how errors are handled, or what the output format looks like. For a tool with no annotations and 4 parameters, this is inadequate.

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 a single, efficient sentence that front-loads the core purpose ('Read memory at specified addresses') and adds necessary context ('after running for some frames'). There is zero waste, and every word earns its place.

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?

Given no annotations and no output schema, the description is incomplete for a tool with 4 parameters and behavioral complexity. It doesn't explain what the tool returns (e.g., memory values, error messages), nor does it cover prerequisites like ROM file format or savestate compatibility. For a read operation with frame execution, more context is needed.

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 description coverage is 100%, so the schema fully documents all 4 parameters. The description adds no parameter-specific semantics beyond implying that addresses are read after frame execution. Since the schema does the heavy lifting, the baseline score of 3 is appropriate, as the description doesn't compensate but doesn't detract either.

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 clearly states the verb 'Read memory' and resource 'at specified addresses', specifying the action and target. It adds context about 'after running for some frames', which distinguishes it from a simple memory read. However, it doesn't explicitly differentiate from sibling tools like mgba_read_range, which likely reads a continuous range rather than discrete addresses.

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?

The description provides no guidance on when to use this tool versus alternatives. It mentions running frames before reading, but doesn't explain when this is necessary or preferable over other tools like mgba_read_range or mgba_dump_entities. There are no explicit when/when-not statements or named alternatives.

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