Skip to main content
Glama

Intact

by io.github.pipeworx-io

Find Interactions

find_interactions
Read-onlyIdempotent

IntAct (EBI) molecular-interaction database — find protein-protein and other molecular interactions for a gene/protein (by name or UniProt id), with detection method, interaction type, organism, PubMed ref, and MI confidence score. Keyless.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNoPage number, 0-indexed (default 0).
limitNoMax interactions to return (default 20, max 100).
queryYesGene name, protein name, or UniProt accession (e.g. "EGFR_HUMAN", "BRCA2", "P04637").

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. Description adds valuable context: data source (IntAct), 'keyless' access, and output fields. No contradictions. Adds appropriate behavioral context beyond annotations.

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?

Single sentence efficiently conveys source, purpose, input, and output. Front-loaded with 'IntAct (EBI) molecular-interaction database'. No redundancy.

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?

Though no output schema, description lists key output fields. Lacks mention of pagination behavior or result format, but schema covers page/limit. Adequate for a simple retrieval tool with good annotation support.

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 coverage is 100% with descriptions for all parameters (page, limit, query). Description repeats parameter examples but does not add new semantics beyond schema. Baseline 3 is appropriate.

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?

Description clearly states the tool finds molecular interactions from IntAct database, specifies input types (gene/protein name or UniProt id), and lists output fields (detection method, interaction type, organism, PubMed ref, MI confidence). It distinguishes from sibling 'interaction_count' by indicating it returns detailed results and is 'keyless'.

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?

No explicit when-to-use or when-not-to-use guidance. The term 'keyless' hints at no authentication needed, but alternatives like 'interaction_count' are not mentioned. Usage context is implied but not clarified.

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

All Intact 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

A4.1/5.0
Disambiguation3/5

Most tools have strong, detailed descriptions with explicit usage guidance, but a few clusters are genuinely ambiguous: ask_pipeworx_beta is currently an exact duplicate of ask_pipeworx, and the Polymarket tools (bet_research, polymarket_edges, polymarket_arbitrage, polymarket_edge_tracker) overlap heavily in purpose. The descriptions help differentiate them, but an agent could still easily select the wrong variant.

Naming Consistency4/5

All tool names are snake_case and most follow an imperative verb-first pattern such as resolve_entity, subscribe, or validate_claim. A few noun-style names like entity_profile, bet_research, and interaction_count deviate, but the consistent underscore style and clear prefixes like polymarket_ and pipeworx_ keep the set predictable.

Tool Count2/5

At 33 top-level tools, the surface is heavy, and several tools are near-duplicates or narrow variants of the same core capability. The broad scope explains some of the count, but the agent-facing API would be cleaner with fewer, more consolidated entry points.

Completeness5/5

The set provides strong lifecycle coverage for its main workflows: querying and grounding, deep research, entity resolution, company profiling, comparisons, Polymarket edge analysis with fill-risk checks, memory storage, and subscription management. There are no obvious dead ends that would prevent an agent from completing a typical task.

Resources