Skip to main content
Glama

CovaSyn Chemistry Tools

covnmr_rank_candidates

Rank several candidate structures against one measured spectrum.

Candidates: `candidates` (list of SMILES), `candidates_csv`
("CCO,CC(=O)O") or `candidates_json`. Spectrum: `path`, else a peak list
(`peaks` / `peaks_json`, `experiments` / `experiments_json`).

GIVE `path` IF YOU HAVE THE FILE: only the file makes the second axis --
overlap of each candidate's full predicted curve with the measured one --
available. Measured on a real 13C APT of a triterpene, the correct
structure ranked first on both axes against n-hexadecane and glucose
(curve 0.37 vs 0.06/0.08). With `path` the order is the curve axis and each
row says whether the peak axis agrees (`agreement`); with a peak list only,
the order is the evidence log-likelihood ratio. The peak axis DECLINES --
`ranking_basis` "declined_unassessable_peak_list", every `rank` null --
when a candidate's evidence cannot be computed (19F/31P, fallback
predictor). Read `ranking_basis` before `ranked`: a null `rank` is the tool
declining to answer, not a tie.

Capped at `max_candidates` (50). With `path` the file decides nucleus,
solvent and field (`nucleus_source`). Multi-step: confirm the winner with
covnmr_verify, or covnmr_sudoku when you have 2D data.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "covnmr_rank_candidates"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNo
peaksNo
api_keyNo
nucleusNo
solventNoCDCl3
field_mhzNo
candidatesNo
peaks_jsonNo
experimentsNo
tolerance_ppmNo
candidates_csvNo
max_candidatesNo
candidates_jsonNo
experiments_jsonNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / candidates
      Added value: +{
      +  "anyOf": [
      +    {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Candidates"
      +}
    • addedInput schema / properties / experiments
      Added value: +{
      +  "anyOf": [
      +    {
      +      "additionalProperties": true,
      +      "type": "object"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Experiments"
      +}
    • addedInput schema / properties / peaks
      Added value: +{
      +  "anyOf": [
      +    {
      +      "items": {
      +        "additionalProperties": true,
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Peaks"
      +}
  2. First observed

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the burden and largely meets it: it discloses that result ordering depends on input mode, that a null `rank` means the tool declined rather than tied (`ranking_basis` "declined_unassessable_peak_list" for 19F/31P or fallback predictor), the 50-candidate cap, and that the file overrides nucleus/solvent/field. It stops short of covering the api_key/auth requirement and tolerance_ppm behavior, which leaves a residual gap for a 14-parameter tool.

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?

Front-loaded with the purpose, then inputs, then the critical `path` guidance, then failure semantics and next steps — a sensible order with little pure filler. It is dense and slightly over-long for the payoff in a couple of spots (the triterpene benchmark anecdote), but nothing is meaningfully wasted.

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

Completeness5/5

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

Given an output schema exists, the description needn't explain return values, and it still pre-empts the one thing the schema cannot convey: that `ranking_basis` should be read before `ranked` and that null ranks are refusals. Combined with input-mode tradeoffs and follow-up routing, an agent has enough to call it correctly.

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 description coverage is 0%, so the description must compensate, and it does for most input parameters: it explains the three candidate formats (with a CSV example), the path vs peaks/peaks_json/experiments/experiments_json split, and max_candidates = 50. It never mentions api_key or tolerance_ppm, and it only implicitly covers nucleus/solvent/field_mhz via the file, leaving several of 14 parameters undocumented anywhere.

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?

The first line states a specific verb and both operands: rank candidate structures against one measured spectrum. The body then distinguishes the two candidate-input families and the two spectrum-input families, and it names the sibling tools (covnmr_verify, covnmr_sudoku) that follow, so an agent can place it in the workflow without opening the schema.

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

Usage Guidelines5/5

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

Explicit conditional guidance: "GIVE `path` IF YOU HAVE THE FILE" with the consequence (second axis only available with a file), plus what happens when only a peak list is supplied. It also ends with a concrete next-step routing to covnmr_verify and covnmr_sudoku. This is about as close to when/when-not/alternatives as a description gets.

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.