Lock a memory address to a specific value in DOSBox, rewriting it every frame like a trainer. Set 1-, 2-, or 4-byte little-endian values.
Lock a memory address to a value. The value is rewritten every frame, trainer-style. Width is 1/2/4 bytes, little-endian.
| Name | Required | Description | Default |
|---|---|---|---|
| value | Yes | Value to hold at the address. | |
| width | No | Width in bytes: 1, 2, or 4 (default 1). | |
| address | Yes | Physical memory address to freeze. |
Changes observed during successful MCP inspections.
v0.2.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only declare readOnlyHint=false, so the agent knows this writes. The description adds genuinely useful behavior beyond that: the value is continuously re-written every frame (persistent lock semantics), and the write is little-endian. It stops short of covering failure modes (invalid address, already-frozen addresses) or how the lock is released.
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 short sentences, zero filler, core action and persistence behavior front-loaded before the width/endianness detail. Nothing redundant with structured fields except the width restatement.
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 mutation tool with only readOnlyHint=false, no output schema, and full schema coverage, this covers the essential mechanics (persistence, width, endianness). It leaves a small gap on lifecycle (how to unfreeze) and error behavior, which is minor given the presence of freeze_clear/freeze_list siblings.
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 100%, so the baseline is 3; the description earns above-baseline by adding little-endian byte order, which the schema does not state and which determines how `value` maps to memory bytes. The width restatement (1/2/4 bytes) duplicates the schema but is harmless.
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 ("Lock a memory address to a value") and the persistence model ("rewritten every frame, trainer-style"), which implicitly separates it from the one-shot mem_write sibling. It does not explicitly name freeze_clear/freeze_list, so differentiation is inferential rather than stated.
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?
"trainer-style" and "rewritten every frame" imply when this tool is appropriate versus a single mem_write, but the description never states when-not to use it, that freeze_clear releases the lock, or how it relates to mem_write/mem_read. Usage is implied rather than guided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.