Skip to main content
Glama
io.github.tammy357/ts-second-opinion

io.github.tammy357/ts-second-opinion

by tammy357

gate_check

Tests candidate transition-state rule code against real and distorted DFT examples, returning pass rates, failing cases, and feedback for revision.

Instructions

Test a candidate rule check against 9,540 real DFT transition states (RDB7 training set) and distorted ones. python_source must define check(rxn, xyz) -> (passed: bool, detail: str); numpy is available as np and math as math; no imports. rxn offers: n, atoms, symbols, reactant_xyz, product_xyz, reactant_bonds, product_bonds ({(i, j): order}), changed_bonds, reaction_centre, neighbours('reactant'|'product'), reactant_chiral_tags, product_chiral_tags. Accepted if it passes >= 99% of real TSs, never crashes, and rejects >= 1% of mirrored or noisy TSs. Returns failing examples and feedback to revise the code.

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": {
      "rule_text": "<rule_text>",
      "python_source": "<python_source>"
    },
    "name": "gate_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
rule_textYes
python_sourceYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A4.4/5.0
Behavior5/5

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

No annotations are provided, so the description carries the full behavioral burden and does well: it states the 9,540-TS corpus, acceptance thresholds (>=99% real, no crashes, >=1% rejection of mirrored/noisy), import restrictions, available modules, and returned failing examples/feedback. It omits runtime and side-effect details but supplies more than enough to predict behavior.

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 long but dense and front-loaded: purpose first, then code contract, environment, acceptance criteria, and return behavior. Every sentence adds operational detail and none is redundant.

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?

For a complex validation harness with no annotations or output schema, it explains the corpus, acceptance rules, callback environment, and return feedback. It is nearly complete, but the unexplained rule_text parameter means an agent cannot fully know what to supply for that required field.

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 0%, so the description must explain both parameters. It thoroughly specifies python_source's callback signature, environment, and rxn fields, but rule_text is only named and never given meaning, such as whether it is a human-readable label or a description used in feedback.

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?

Names a specific verb ('Test') and resource ('candidate rule check') plus the evaluation corpus, so an agent can tell this is validation rather than saving or retrieving rules. It is clearly distinct from siblings like save_rule and get_rule_source.

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?

It establishes a clear context for use: testing a candidate rule check against real and distorted transition states. However, it does not explicitly state when not to use it or name an alternative sibling for related tasks, so it lacks full when/when-not guidance.

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