Infers stack locals, globals, arguments, return values, and register roles from MIPS dataflow observations, returning evidence-backed candidates rather than automatic source edits.
Infer stack locals, globals, arguments, returns and register roles from MIPS dataflow observations. Results are candidates with evidence, not automatic source edits.
| Name | Required | Description | Default |
|---|---|---|---|
| hex | Yes | ||
| arch | No | ||
| address | No |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does disclose one important trait: results are advisory candidates with evidence, not automatic source edits, implying a read-only analysis that does not mutate the repo. It leaves other behavioral facts unstated — whether a project/ROM must be loaded first, what the hex blob must contain, whether analysis is deterministic or expensive, and what the evidence structure looks like.
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, front-loaded with the core capability and followed by the key caveat about output trustworthiness. Nothing is redundant or padded.
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?
The qualitative nature of the return value is described despite there being no output schema, which is valuable, but input requirements for a 3-parameter tool with zero schema documentation remain unexplained. An agent knows what the tool produces conceptually but not how to prepare a valid call.
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 0% across three parameters, so the description must compensate and does not. It never explains the required "hex" string (raw bytes? hexdump text? how much code?), what "address" anchors the dataflow to, or that "arch" selects between the N64 (r4300i) and PS2 (r5900) register models — all left for the agent to guess.
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 ("Infer") and resource plus a concrete enumeration of what is inferred: stack locals, globals, arguments, returns, register roles, and names the input source (MIPS dataflow observations). An agent can tell this apart from infer_structs or suggest_variable_names in substance, though no sibling is explicitly named.
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?
Usage is only implied by the reverse-engineering context (MIPS dataflow). There is no explicit when-to-use, no prerequisites, and no routing to the obvious alternatives in the sibling set such as infer_structs, suggest_variable_names, or validate_variable_map. The second sentence usefully frames how to treat the output but does not say when to call the tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.