Get drug/compound data from PubChem (NIH). Returns CID, IUPAC name, molecular formula, molecular weight, canonical SMILES, InChI, description, and synonyms.
| Name | Required | Description | Default |
|---|---|---|---|
| cid | No | PubChem CID number (alternative to name) | |
| name | No | Drug or compound name (e.g. aspirin, caffeine, ibuprofen) | aspirin |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must convey operational behavior. It indicates the data source (PubChem/NIH) and that it returns a set of fields. However, it does not explicitly state that the operation is read-only, nor does it mention potential side effects or limitations like external API dependency or default parameter behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two concise sentences, front-loaded with the primary action 'Get drug/compound data', followed by an efficient list of returned fields. There is no redundant or excessive text.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite listing return fields, the description omits important operational details: both parameters are optional with a default of 'aspirin', there is no mention of parameter precedence or behavior when both are provided, and no output schema exists to clarify the response structure. This leaves the agent with unanswered questions for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides 100% coverage with descriptions for both 'cid' and 'name'. The tool description does not add additional parameter semantics beyond what the schema states, so the baseline of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it retrieves drug/compound data from PubChem and enumerates the specific fields returned. It distinguishes from get_drug_targets by listing data fields, but does not explicitly differentiate from get_drug_info.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is for fetching compound data, but it does not state when to choose it over sibling tools like get_drug_info or get_drug_targets. There is no explicit guidance on parameter selection or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool queries a distinct public database (PubChem, OpenFDA, ChEMBL) and returns clearly non-overlapping data types: chemical properties, label/safety info, and target/bioactivity. Despite the shared drug/compound domain, the descriptions leave no ambiguity about which tool to use.
All tool names follow the exact pattern 'get_' + descriptive noun phrase (compound_data, drug_info, drug_targets), making the naming scheme highly predictable and consistent.
With only three tools, the server is minimal yet well-scoped for its purpose of retrieving drug/compound information from multiple sources. Each tool adds a distinct value and the count is within the ideal range for a focused server.
The server covers three major aspects of drug information: chemical identifiers, regulatory/safety data, and target/bioactivity. However, there is no search/discovery tool to locate drugs by query, and additional areas like clinical trials or pricing are missing. Still, the core lifecycle of drug data lookup is adequately covered.