Skip to main content
Glama

Get Compound Details

pubchem_get_compound_details
Read-onlyIdempotent

Retrieve detailed compound information by PubChem CID: physicochemical properties, descriptions, synonyms, drug-likeness, and pharmacological classification.

Instructions

Get detailed compound information by CID. Returns physicochemical properties (molecular weight, SMILES, InChIKey, XLogP, TPSA, etc.), optionally with a textual description (pharmacology, mechanism, therapeutic use), known synonyms, drug-likeness assessment (Lipinski/Veber rules), and/or pharmacological classification (FDA classes, MeSH classes, ATC codes). Accepts up to 100 CIDs per call.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cidsYesPubChem Compound IDs to fetch (1-100). Resolve from names/SMILES with pubchem_search_compounds.
propertiesNoProperties to retrieve. Defaults to a core set: MolecularFormula, MolecularWeight, IUPACName, CanonicalSMILES, IsomericSMILES, InChIKey, XLogP, TPSA, HBondDonorCount, HBondAcceptorCount, RotatableBondCount, HeavyAtomCount, Charge, Complexity.
maxSynonymsNoMax synonyms returned per compound per page (1-100). PubChem lists hundreds for common drugs; use synonymOffset to reach the ones past this page. Default: 20.
synonymOffsetNoZero-based index of the first synonym to return within each compound's synonym list. The same offset is applied to every compound in the batch. Pass the nextSynonymOffset from a previous call to read the following page. Default: 0.
includeSynonymsNoFetch known names and synonyms (trade names, systematic names, registry numbers), paged via synonymOffset/maxSynonyms. Fetched for every found CID in the batch. Slower for large CID lists.
maxDescriptionsNoMax number of distinct description entries per compound per page (1-20). PubChem returns near-duplicate summaries from many depositors; duplicates are collapsed before this cap applies. Default: 3.
descriptionOffsetNoZero-based index of the first description to return within each compound's description list. The same offset is applied to every compound in the batch. Pass the nextDescriptionOffset from a previous call to read the following page. Default: 0.
includeDescriptionNoInclude textual descriptions (pharmacology, mechanism, therapeutic use) attributed by source. Well-studied compounds have many overlapping summaries — paged via descriptionOffset/maxDescriptions. Fetched only for the first 10 CIDs in the batch; remaining CIDs return without descriptions and are listed in the response's skippedCids.
includeDrugLikenessNoCompute drug-likeness assessment: Lipinski Rule of Five (MW, XLogP, HBD, HBA) and Veber rules (TPSA, rotatable bonds). Computed from the returned properties, so it adds no latency.
includeClassificationNoInclude pharmacological classification: FDA Established Pharmacologic Classes, mechanisms of action, MeSH classes, and ATC codes. Fetched only for the first 10 CIDs in the batch; remaining CIDs return without classification and are listed in the response's skippedCids.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
noticeNoRecovery guidance covering the skipped CIDs, an offset that runs past every compound, and pages that remain. Absent when nothing was skipped or truncated.
compoundsYesCompound detail records.
skippedCidsNoCIDs found in PubChem whose descriptions and classification were NOT fetched because the batch exceeded the per-call fan-out limit. Their absence from a record means "not requested", not "PubChem has none" — re-request these CIDs in a follow-up call. Present only when CIDs were skipped.
enrichedCidsNoCIDs whose descriptions and classification were fetched. Present only when the batch exceeded the per-call fan-out limit and other CIDs were skipped.
synonymOffsetNoZero-based index of the first synonym returned within each compound's list. Present when includeSynonyms is true.
descriptionOffsetNoZero-based index of the first description returned within each compound's list. Present when includeDescription is true.
nextSynonymOffsetNosynonymOffset to pass on the next call to continue past this page. Omitted when no compound in the batch has further synonyms.
nextDescriptionOffsetNodescriptionOffset to pass on the next call to continue past this page. Omitted when no compound in the batch has further descriptions.
Behavior4/5

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

Annotations already declare readOnly, openWorld, and idempotent hints. The description adds critical behavioral details: caps on descriptions/classification (first 10 CIDs only), pagination via offsets, and default property sets. This goes beyond annotation coverage without contradiction.

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 concise (3-4 sentences) and front-loaded: first sentence states the core purpose, followed by bullet-like lists of return types. Every sentence earns its place; no redundant or vague phrasing.

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 the tool's complexity (10 parameters, nested pagination, first-10-only constraints), the description completely covers key behaviors: input limits, default properties, pagination for synonyms/descriptions, and the skippedCids fallback. The presence of an output schema is noted but not needed to detail.

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?

All 10 parameters have schemas with descriptions, achieving 100% coverage. The description adds value by explaining defaults (e.g., property set, synonym offset behavior), performance impacts (slow for large synonym lists), and pagination mechanics. This meaningfully extends beyond the schema.

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 description clearly states it retrieves detailed compound information by CID, listing specific data types (physicochemical properties, textual description, synonyms, drug-likeness, pharmacological classification). It distinguishes itself from sibling tools like pubchem_search_compounds (which resolves names to CIDs) and pubchem_get_compound_image.

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?

The description notes the CID input limit (100 per call) and directs users to pubchem_search_compounds for name/SMILES resolution. It implicitly communicates usage context (when you have CIDs) but does not explicitly contrast with sibling tools like pubchem_get_summary for simpler needs.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/cyanheads/pubchem-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server