Skip to main content
Glama

simulation_sample

Destructive

Samples live native DSIM network STATE values and saves evidence using native network names, not semantic JSON net names; raw results include strength bits.

Instructions

Sample live native DSIM network STATE values and save evidence. Supply native network names, not semantic JSON net names. Raw states include strength bits.

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": {
      "session": "<session>",
      "nets": "<nets>"
    },
    "name": "simulation_sample"
  }
}

Input Schema

NameRequiredDescriptionDefault
netsYes
secondsNo
sessionYes
interval_msNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.1/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered; the description adds that it samples live state, saves evidence, and that raw states carry strength bits. However, it never explains what "saving evidence" touches or overwrites, nor that sampling occupies up to 25 seconds, which is exactly what a destructive-hinted tool should disclose. Annotation contradiction is not present – sampling plus saving evidence is consistent with a non-readonly write.

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?

Three short sentences, front-loaded with the action and its side effect, then the naming constraint, then a detail about return values. Nothing is padded, though the last sentence's phrasing ("strength bits") is terse enough to be ambiguous.

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

Completeness2/5

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

With no output schema, four undocumented parameters, and a destructive annotation, the definition should say what evidence is written and where, plus how seconds/interval_ms shape the capture. As written, an agent can identify the tool but cannot confidently predict its side effects or parameter behavior.

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%, so the description carries the full burden for four parameters. It meaningfully clarifies only `nets` ("Supply native network names, not semantic JSON net names") and leaves `session`, `seconds`, and `interval_ms` completely unexplained, including the sampling-duration/burst semantics that matter for a bounded 1–25 second capture.

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 ("Sample") against a specific resource (live native DSIM network STATE values) and names a side effect ("save evidence"). The distinction from simulation-like siblings is implied by "live native ... values" but no sibling is named, so it stays below a 5.

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?

Usage is implied – sampling a running simulation – but there is no explicit when-to-use versus when-not, and no routing to alternatives such as simulation_observe or live_read. The only guidance offered is about how to name the nets, not when to call this tool.

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