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

io.github.tammy357/ts-second-opinion

by tammy357

triage_structures

Triage transition-state guesses from any generator by comparing reactant, product, and guess geometries, flagging model disagreement, and returning inferred SMILES for validation.

Instructions

Triage your own reaction, from any TS generator and with any elements. Give the reactant and product geometries and one or more TS guesses as xyz text (multi-frame xyz allowed); several guesses enable the model-disagreement signal. mapped_reaction_smiles is optional: without it, bonds, bond orders and stereocentres are read from the reactant and product geometries (every file must then list the same atoms in the same order) and the inferred SMILES is returned for checking; charge and multiplicity then default to 0 and 1. With a SMILES (every atom, hydrogens too, mapped 1..N), order='map' if atoms are listed by atom-map number, 'smiles' if listed in the order they appear in the SMILES, and charge and multiplicity are read from it.

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": {
      "reactant_xyz": "<reactant_xyz>",
      "product_xyz": "<product_xyz>",
      "guesses_xyz": "<guesses_xyz>"
    },
    "name": "triage_structures"
  }
}

Input Schema

NameRequiredDescriptionDefault
orderNomap
chargeNo
guesses_xyzYes
product_xyzYes
multiplicityNo
reactant_xyzYes
mapped_reaction_smilesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations present, the description carries the full burden and does so well: it discloses that multiple guesses enable a model-disagreement signal, that multi-frame xyz is accepted, that every geometry file must list atoms in the same order, and that charge/multiplicity default to 0 and 1. It stops short of describing runtime cost or failure behavior, but the key input-contract behaviors are exposed.

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?

The purpose and required inputs are front-loaded, and each sentence adds real information about defaults, ordering or mode selection. It is a dense single block with some run-on clauses, but little is wasted.

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 7-parameter tool with no annotations and no output schema, the description does substantial work: it explains modes, defaults, ordering constraints and that an inferred SMILES is returned for checking. Remaining gaps are minor, such as no mention of error conditions or what the triage result itself contains.

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

Parameters5/5

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

Schema description coverage is 0%, so the description must compensate and it does: reactant_xyz, product_xyz and guesses_xyz are explained as xyz text (multi-frame allowed), mapped_reaction_smiles is described as optional with an atom-map 1..N requirement, order is defined as 'map' vs 'smiles' ordering, and charge/multiplicity are tied to defaults and SMILES inference. Nearly every one of the 7 parameters gains meaning beyond the bare schema types.

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 uses a specific verb and resource: 'Triage your own reaction' plus 'from any TS generator and with any elements'. An agent can tell this is a transition-state triage tool that takes geometry inputs. However, it never distinguishes itself from siblings like triage_reaction or triage_batch, so the boundary between them is left implicit.

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?

It gives strong conditional guidance about the optional mapped_reaction_smiles path (geometry-only mode vs SMILES mode), which helps the agent decide between sub-modes. But it never states when to pick this tool over triage_reaction or triage_batch, and there is no explicit when-not guidance, so guidance is implied rather than complete.

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