Skip to main content
Glama

find_common_substructure

Read-only

The maximum common substructure of a set of small molecules (RDKit FindMCS): the largest core every structure shares, as SMARTS, with its atom and bond count.

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": {
      "molecules": "<molecules>"
    },
    "name": "find_common_substructure"
  }
}

Input Schema

NameRequiredDescriptionDefault
_filesNoThe project: record references shaped like _subject. Their records become library documents a tool names in sequences/parts/document; a trace or alignment is found by file name.
timeoutNoseconds before RDKit stops searching. The MCS problem is NP-hard, so a large diverse set can run long; a run that stops early reports its core as a lower bound. In s. Advanced.
_subjectNoThe record to act on: exactly one of sequence, accession (+source), sample (an id from list_samples) or file ({name, text} or {name, base64}); record_index picks one record of several.
moleculesYesthe structures: one SMILES or molfile per entry.
complete_rings_onlyNoa ring is in the core whole or not at all — the core a chemist would draw. Off, RDKit may return a partial ring, which is a valid substructure and a strange thing to call a scaffold.
ring_matches_ring_onlyNoa ring atom only matches another ring atom, so a chain carbon never maps onto a ring one.

Output Schema

NameRequiredDescriptionDefault
smartsYesthe common core as SMARTS — wire it into decompose_r_groups as `core`
unreadYesinput indices RDKit could not read
summaryYesthe common core in words, generated from this run
canceledYesthe search hit the timeout, so this core is a LOWER BOUND and a longer run may find a larger one
numAtomsYesatoms in the core
numBondsYesbonds in the core

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds the upstream identity (RDKit FindMCS) and the return shape (SMARTS plus atom/bond counts), but it does not itself disclose the anytime-search behavior, the timeout semantics, or the lower-bound caveat — those live only in the schema's parameter text.

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?

A single sentence with zero filler: the operation, its implementation, the conceptual meaning of the result, and the output type are all front-loaded. Nothing is redundant or vague.

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?

With an output schema present and fully documented parameters, the description only needs purpose framing, which it supplies precisely. The only small gap is that it doesn't state how the result behaves when no common substructure exists — an edge case the output schema may cover.

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 100%, including detailed explanations of timeout lower-bound behavior and the two ring flags, so the schema does the heavy lifting. The description adds no parameter-specific meaning beyond what the schema already provides; baseline 3 applies.

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?

States a specific operation and resource: 'maximum common substructure of a set of small molecules (RDKit FindMCS)', plus what is returned ('the largest core every structure shares, as SMARTS, with its atom and bond count'). An agent can immediately tell this is a cheminformatics MCS tool and not the sequence-motif siblings like find_linear_motifs.

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?

The 'of a set of small molecules' framing implies when the tool applies (multi-structure comparison), and the schema's timeout note warns that large diverse sets can run long. But the description states no explicit when-to-use/when-not-to-use criteria and names no alternative tool for single-vs-multi structure or sequence-level comparisons.

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