Skip to main content
Glama

simulation_decode_display

Destructive

Decode saved simulation traces by segment and digit net values to produce composite display frames with confirmations and rejected samples from stable sampled states.

Instructions

Decode a saved raw simulation_observe/stimulate JSON trace by actual segment/select net values. Supply source SHA-256, ordered A..G[,DP] segment_nets and left-to-right digit_nets. Requires exactly one selected digit and known stable states; reports composite frames, confirmations and rejected samples. This is sampled digital evidence, not optical output or complete transitions.

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": {
      "trace_path": "<trace_path>",
      "expected_sha256": "<expected_sha256>",
      "segment_nets": "<segment_nets>",
      "digit_nets": "<digit_nets>"
    },
    "name": "simulation_decode_display"
  }
}

Input Schema

NameRequiredDescriptionDefault
digit_netsYes
trace_pathYes
digit_activeNo
max_frame_msNo
segment_netsYes
segment_activeNo
expected_sha256Yes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

The description adds genuine behavioral context beyond the annotations: it reports composite frames, confirmations and rejected samples, and explicitly warns the result is sampled digital evidence, not optical output or complete transitions. That fidelity caveat is valuable. It does not address why the tool is flagged destructiveHint=true and readOnlyHint=false, which is unexplained for something described purely as reading a saved trace.

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?

Dense but front-loaded: the action comes first, then the required inputs, then constraints, then the fidelity caveat. Every sentence carries information, though the technical shorthand (A..G[,DP]) makes it harder to parse than it needs to be.

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?

For a 7-parameter tool with no output schema, the definition covers the required-parameter semantics well but leaves the optional knobs and the actual return shape underspecified ('reports composite frames, confirmations and rejected samples' is not enough to know what an agent can read back). Adequate, but with clear gaps 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.

Parameters4/5

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

With 0% schema description coverage the description must carry the load, and it adds real meaning: segment_nets is ordered A..G with optional DP (matching the 7-8 item bounds), digit_nets is left-to-right, expected_sha256 is the source hash, and 'exactly one selected digit' implies the polarity behavior. The three optional parameters (segment_active, digit_active, max_frame_ms) are left entirely undocumented, keeping it below a 5.

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?

States a specific verb and resource: decode a saved raw simulation_observe/stimulate JSON trace into segment/digit net values, and names the sibling tools that produce such traces. An agent can tell this is a post-hoc analysis tool rather than a live simulation tool. It stops just short of naming an explicit contrast alternative, but the source-tool reference does most of the disambiguation work.

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?

Prerequisites are given clearly (SHA-256 of source, ordered A..G[,DP] segment nets, left-to-right digit nets, exactly one selected digit, known stable states), which implies when the tool applies. However, there is no explicit when-to-use versus when-not-to-use guidance relative to siblings like simulation_observe or simulation_sample, nor an explanation of what happens if the trace is unstable or the hash mismatches.

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