Skip to main content
Glama

BioBTree

by bio.sugi

biobtree_search

Search 70+ biological databases.

SYNTAX: biobtree_search(terms="entity")

BEFORE SEARCHING - Use your training knowledge to plan:

  1. What type of entity is this? (disease, process, drug, gene, protein)

  2. What is the query asking for? (drugs, genes, function, etc.)

  3. What equivalent terms might give better results? (e.g., "temperature homeostasis" is a process → related condition is "fever")

  4. Choose best entry point for query type (disease terms for drug queries)

WORKFLOW:

  1. Search WITHOUT dataset filter first (discover where entity exists)

  2. Use IDs from results with biobtree_map

QUERY PATTERNS (choose based on question):

"DRUG FOR DISEASE/CONDITION X":

  • Prefer disease terms (mesh/mondo/efo) over GO terms for drug queries

  • If search only returns GO term, search for the related CONDITION instead (e.g., "temperature homeostasis" → search "fever" instead)

  • Search disease → mondo → clinical_trials → chembl_molecule

  • OR search drug class directly (e.g., "antipyretic", "NSAID", "antibiotic")

  • Verify mechanism for top 2-3 drugs only (don't enumerate all proteins!)

"DRUG TARGETS" (use BOTH paths for complete picture):

  • chembl: >>chembl_molecule>>chembl_target>>uniprot (mechanism-level)

  • pubchem: >>pubchem>>pubchem_activity>>uniprot (protein-level, often 50+ targets)

  • Filter approved: >>chembl_molecule[highestDevelopmentPhase==4]

"DISEASE GENES":

  • Search disease → mondo/hpo → gencc/clinvar/orphanet → hgnc

"PROTEIN FUNCTION":

  • Search protein → uniprot → go/reactome

"MECHANISM QUERIES" (drug-disease):

  • Use biobtree_entry to see what's connected (xrefs)

  • Check EDGES to see where each xref leads

  • Follow connections relevant to your question

  • Build chain: Drug → Target → [connections] → Disease

RETURNS: id | dataset | name | xref_count

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNoPagination token
termsYesComma-separated identifiers to search
datasetNoFilter to specific dataset (omit for discovery)

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 full burden. It discloses return format ('RETURNS: id | dataset | name | xref_count') and explains fallback behavior (e.g., searching for related condition if only GO term is found). It does not mention rate limits or pagination details, but the behavioral guidance is substantial.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with sections and clear formatting, but it is quite long and includes verbose examples (e.g., the 'temperature homeostasis' scenario). While useful, it could be tightened without losing value, so it's not a model of conciseness.

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?

Given the tool's complexity and lack of output schema, the description covers return format, search strategies, and workflow integration with sibling tools. It does not explain pagination behavior or result limits, but overall it is sufficiently complete for an agent to use effectively.

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 baseline is 3. The description adds strategic meaning beyond the schema: it explains how to choose 'terms' (e.g., disease terms for drug queries) and advises omitting the dataset filter for discovery. This enriches the parameter semantics.

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 'Search 70+ biological databases' with a specific verb and resource. It differentiates from siblings by framing itself as the discovery/search entry point, with explicit references to biobtree_map and biobtree_entry in workflows.

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?

Provides extensive when-to-use guidance: 'Search WITHOUT dataset filter first', 'Use IDs from results with biobtree_map', and explicitly names biobtree_entry for mechanism queries. It also gives query patterns for different question types (drug-for-disease, drug targets, disease genes, protein function).

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

All BioBTree toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0
Disambiguation5/5

Each tool has a distinct role: atlas for curated summaries, entry for full entry details, map for identifier mapping, and search for cross-database discovery. The descriptions clearly delineate when to use each, with workflow examples reducing any potential confusion.

Naming Consistency4/5

All tool names share the 'biobtree_' prefix and use lower_snake_case. The suffixes mix nouns (atlas, entry) and verbs (map, search), but this is consistent with their function and does not hinder readability or predictability.

Tool Count5/5

Four tools provide a well-scoped abstraction over 70+ databases. Each tool covers a distinct necessity: discovery, mapping, detailed lookup, and curated summaries. This is a solid, minimal set for the stated purpose.

Completeness5/5

The tool surface covers the full lifecycle of biological data exploration: search to find identifiers, map to translate between databases, entry to inspect connections and attributes, and atlas for citable summaries. No obvious dead ends; the workflow examples ensure agents can traverse the data graph effectively.

Resources