Skip to main content
Glama

Lone Pair

Draw a reaction scheme

render_reaction
Read-onlyIdempotent

Draw a reaction scheme from its parts: reactants joined by plus signs, an arrow with optional text above and below, then products. Each structure is SMILES, InChI or a molfile. For a reaction already written as reaction SMILES, use draw. Refused, with the reason, instead of drawn wrongly: SMILES that cannot be read, aromatic rings that cannot alternate single and double bonds, and atoms with too many bonds (unless as_written). The result carries drawing (Lone Pair JSON to pass to edit_drawing or back in as input) and notes (anything changed on reading or lost in the format).

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": {
      "reactants": "<reactants>",
      "products": "<products>"
    },
    "name": "render_reaction"
  }
}

Input Schema

NameRequiredDescriptionDefault
dpiNoPNG resolution, 300 by default; 600 for print.
aboveNoText above the arrow: reagents or catalyst. Digits after letters become subscripts (H2SO4).
belowNoText below the arrow: solvent, temperature, time.
styleNoJournal style. acs = ACS Document 1996 (default), rsc = RSC, nature = Nature Reviews, slides = heavier lines for slides.
formatNopng (default; returned as an image), svg (returned as text), pdf or eps (returned as base64 in `data_base64`).
opaqueNoWhite background instead of transparent (SVG, PNG). Default false.
productsYesStructures right of the arrow.
reactantsYesStructures left of the arrow.
as_writtenNoDraw atoms that have too many bonds instead of refusing the structure. Default false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description goes further by disclosing refusal-with-reason behavior rather than silent misdrawing, plus what the result carries (`drawing`, `notes`) and that `notes` records changes made on reading or lost in the format. The only gap is that it doesn't mention performance/limits or how a refusal surfaces (error vs. field).

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?

Four sentences, front-loaded with purpose and composition model, then the alternative tool, then refusal conditions, then return payload. The refusal sentence is dense but each clause is load-bearing and no sentence restates the name or title.

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?

For a 9-parameter tool with no output schema, the description supplies the missing return-value information (`drawing` as Lone Pair JSON reusable in `edit_drawing` or as `input`, plus `notes`) and covers failure modes. Nothing an agent needs to invoke it correctly or interpret the result is absent.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds real semantics: it tells the agent that `reactants`/`products` accept SMILES, InChI or molfile, and that `above`/`below` correspond to reagents/catalyst and solvent/temperature/time respectively, i.e. reaction-role meaning the schema does not express. It adds nothing about `dpi`, `style`, `format` or `opaque`, which the schema already handles well.

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 opening sentence states a specific verb and resource ('Draw a reaction scheme') and spells out the composition model: reactants joined by plus signs, arrow with optional text above and below, then products. It also distinguishes itself from the sibling `draw` for the reaction-SMILES case, so an agent can pick between them without opening a 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 routing is given: 'For a reaction already written as reaction SMILES, use draw,' which is exactly the when-to-use-vs-alternative signal needed. It also defines when the tool will refuse (unreadable SMILES, non-alternating aromatic rings, excessive valence) and the `as_written` escape hatch, which functions as a usage condition.

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.

Resources