Skip to main content
Glama

execute_distributed_matmul

Executes verified distributed matrix multiplication C = A x B across decentralized GPU workers with dynamic Freivalds verification and L402 settlement. Accepts file paths (.npy, .npz, .safetensors) or inline 2D JSON arrays.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "matrix_a": "<matrix_a>",
      "matrix_b": "<matrix_b>"
    },
    "name": "execute_distributed_matmul"
  }
}

Input Schema

NameRequiredDescriptionDefault
dtypeNoComputation precision ('fp32', 'fp16', 'bf16').fp32
matrix_aYesFile path (.npy/.npz/.safetensors) or inline 2D array for matrix A (M x K).
matrix_bYesFile path (.npy/.npz/.safetensors) or inline 2D array for matrix B (K x N).
tile_sizeNoOptional tile block size override.
output_pathNoOptional output file path (.npy, .npz, or .safetensors) to write C.
tensor_key_aNoOptional tensor key when loading matrix_a from .safetensors or .npz.
tensor_key_bNoOptional tensor key when loading matrix_b from .safetensors or .npz.
partitioning_strategyNoMatrix partitioning topology.output_grid_2d

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.3/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full burden, and it does disclose meaningful behavior: work is distributed across decentralized workers, results are verified via dynamic Freivalds checks, and settlement happens over L402. It does not say what happens when verification fails, whether payment is charged on failure, or whether C is returned inline versus only written to output_path.

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?

Two tightly written sentences with the core operation front-loaded and the input-format note second. No filler, no restatement of the tool name.

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

Completeness3/5

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

This is a complex, asynchronous, paid, distributed operation with 8 parameters and no output schema, so the description should say what a caller gets back and what failure looks like. It omits the return value entirely (inline result vs. file written to output_path) and says nothing about latency, cost, or error behavior, leaving a real gap for a tool of this complexity.

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

Parameters3/5

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

Schema coverage is 100%, so every one of the 8 parameters is already documented in the schema. The description's second sentence only restates the accepted matrix input formats, which the schema already specifies, and adds nothing about dtype, tile_size, or partitioning_strategy. Baseline 3 is appropriate.

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

Purpose4/5

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

The description names a specific verb and resource ("Executes verified distributed matrix multiplication C = A x B") plus the execution substrate (decentralized GPU workers), so the operation is unambiguous. It stops short of naming any sibling or contrasting itself with e.g. estimate_job_cost, which keeps it at 4 rather than 5.

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

Usage Guidelines2/5

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

The only usage-adjacent statement is about accepted input forms (file paths or inline arrays). There is no guidance on when to prefer this tool over cost estimation or status checks, no mention of prerequisites such as an L402 wallet/credential, and no stated limits on matrix size.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.