Skip to main content
Glama

SizeMyFile

Plot a tensor histogram

tensor_histogram
Idempotent

Read one F32 or F64 Safetensors tensor and group finite values into histogram bins. Count NaN and infinity separately. Static parsing within a 32 MiB combined input budget. No inference, Python imports or pickle execution. Reported compatibility is structural, not a guarantee a framework will load a model. Tensor name is required when the file contains more than one tensor. Queues a run and returns its ID for progress and output tracking. Uses cloud allowance.

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": {
      "artifacts": "<artifacts>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "tensor_histogram"
  }
}

Input Schema

NameRequiredDescriptionDefault
optionsNo
artifactsYes
idempotency_keyYes
allow_server_fallbackNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.4/5.0
Behavior4/5

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

The description adds substantial behavior that the annotations do not carry: the job is queued asynchronously and returns an ID, parsing is static under a 32 MiB budget, no imports or pickle execution occur, cloud allowance is consumed, and reported compatibility is explicitly not a load guarantee. These are exactly the operational facts (quota cost, async lifecycle, safety boundary) an agent needs before committing. It stops short of describing failure modes or what happens when the 32 MiB budget is exceeded, which keeps it off a 5.

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

Conciseness4/5

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

Sentences are short and declarative, with the core operation front-loaded and the constraints following in a sensible order. It is dense but nearly every clause carries a distinct fact; the one arguable redundancy is restating both the queueing behavior and the run ID, which are two halves of the same fact.

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?

An output schema exists, so the return values need not be explained and the brief mention of a run ID suffices. Against that, this is a nested-object, async, quota-consuming tool with 0% schema description coverage, and three of four parameters receive no explanation at all, which leaves a visible hole in an otherwise thorough definition.

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

Parameters2/5

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

Schema description coverage is 0% across four parameters, so the description must compensate and largely does not. It addresses only the tensor name and the notion of histogram bins; the artifacts array (1-50 UUIDs), the idempotency_key, and allow_server_fallback are never explained, leaving an agent to guess at input requirements for a job that consumes cloud allowance.

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?

"Read one F32 or F64 Safetensors tensor and group finite values into histogram bins" is a specific verb plus resource with a precise computational outcome, and the NaN/infinity handling further narrows the behavior. It does not, however, explicitly contrast itself with the adjacent tensor_extract or tensor_scan tools, so an agent must infer the division of labor from the sibling names alone.

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

Usage Guidelines3/5

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

The description gives one conditional rule of real value: the tensor name is required when the file holds more than one tensor. Beyond that, the when-to-use context is only implied by the stated purpose, and there are no exclusions or named alternatives telling an agent when to prefer tensor_scan or tensor_extract instead.

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.