Skip to main content
Glama

fuzz_hook

Identifies a Hook's accept/rollback boundary by executing its bytecode on deterministically generated inputs, sweeping tx types, amounts, and account fields to reveal accepting and rejecting inputs.

Instructions

DIFFERENTIAL FUZZER: finds a Hook's accept/rollback decision boundary by running its REAL bytecode through the local VM against many DETERMINISTICALLY generated inputs (no randomness, no clock — fully reproducible). Sweeps axes you request: txType (a supplied list or all tx types), a raw otxn Amount-field byte range, otxn account/destination ids, and named otxn params. Reports counts {accept,rollback,halted,degraded}, per-axis boundary findings, and concrete accepting/rejecting sample inputs. Honest: degraded/halted runs are counted but excluded from the boundary; if every run degrades/halts it says INCONCLUSIVE and why. fidelity LOCAL_VM_FUZZ.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
stateNo
txTypeNobase originating tx type
feeBaseNo
samplesNonumber of generated inputs (default 64, max 512)
txTypesNotxType axis: tx types to sweep, e.g. ["Payment","Invoke"]. Default: all known tx types (capped).
wasmHexNo
amountMaxNoAmount axis high (raw drops)
amountMinNoAmount axis low (raw drops; field bytes are NOT STAmount-encoded)
ledgerSeqNo
hookParamsNo
otxnFieldsNo
otxnParamsNo
paramSweepNonamed otxn params -> candidate hex values to sweep
wasmBase64No
amountFieldNootxn field id to write the Amount sweep into (default 6)
sweepAccountNoalso sweep a few deterministic account ids
hookAccountIdNo
sweepDestinationNoalso sweep a few deterministic destination ids
Behavior5/5

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

Despite no annotations, the description provides extensive behavioral details: determinism (no randomness/clock), reporting of counts, boundary findings, sample inputs, and honest handling of degraded/halted runs (excluded, inconclusive if all fail). This fully compensates for missing annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single dense paragraph that front-loads the core purpose and efficiently covers axes, reporting, and honesty. Every sentence adds value with no repetition or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description explains the tool's behavior, inputs, and outputs (counts, boundaries, sample inputs) thoroughly given the complexity. However, it does not detail all 18 parameters (e.g., state, feeBase, ledgerSeq), which are left to the schema. The overall completeness is high but not exhaustive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 50%, and the description adds meaning by explaining the axes (e.g., txType, amount range, account/destination ids) and their roles. It clarifies the purpose of parameters like amountMin/amountMax and mentions wasmHex/wasmBase64 for bytecode. However, some parameters (state, feeBase, otxnFields) remain unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool is a 'DIFFERENTIAL FUZZER' for finding a Hook's decision boundary by running real bytecode with deterministic inputs. It specifies the resource (Hook) and action (fuzz to find boundaries), and the detailed axes distinguish it from sibling tools like simulate_hook_trigger.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description outlines when to use the tool (for fuzzing hooks to find decision boundaries) but does not explicitly mention when not to use it or suggest alternatives. The context is clear, but no exclusions are stated.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Hugegreencandle/xahau-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server