Composio

Customize tool schemas before agents see them

Composio’s schema modifiers let you rewrite a tool’s schema before it reaches an agent. Use them to adjust descriptions, add or hide parameters, and set defaults when the raw tool schema needs guardrails.

Agenticness = how independently a tool can take action, scored across 9 dimensions. Scored independently by David Kooi, Skylark Creations — see full rubric →

See pricing ↓

API

Chrome Extension

Integrations

B2B

For Developers

For Teams

Visit Composio

Is this your tool? Claim this listing to manage your content and analytics.

Recent activity

What's happened with Composio lately

May 23, 2026
Score change
Rubric upgrade v3_0 → v3.1: score 1/32 → 9/361 → 9/36(+8)
Rubric upgrade: agenticness v3.0 (8 dims, /32) → v3.1 (9 dims, /36). Adds Dim 9 (Operator Sovereignty), splits Dim 6 into 6a/6b lenses, tightens Dim 4 autonomous-retry distinction. Not a product change — score shift reflects new dimension + recalibrated rubric, not a change in the tool. Fanout suppressed.
See the news that prompted this

News mentions sourced from our news feed; score changes from periodic re-evaluations.

Ask about Composio

Get answers based on Composio's actual documentation

Try asking:

About

What It Is

Schema Modifiers are a Composio SDK middleware feature for developers building agents with external tools. They sit between your tool registry and the agent, letting you change how a tool appears before the model decides whether and how to use it.

What to Know

This is not a standalone agent product; it is a low-level customization layer for Composio tool schemas. It can help when an agent needs clearer instructions or when certain arguments should be required, removed, or given defaults, but it does not...

Key Features

Rewrites a tool’s schema before it is shown to an agent

Can modify tool descriptions to provide extra usage guidance

Can add new arguments to a tool schema

Can hide irrelevant arguments from a tool schema

Can set default values for tool arguments

Use Cases

Guide an LLM to use a default GitHub repository when listing issues

Remove unused parameters from a tool to reduce agent confusion

Make a key argument required so tool calls fail less often

Agenticness: Guided Assistant

Executes tasks you assign, one step at a time, within narrow domains.

High evidence

Last evaluated: May 23, 2026

Dimension Breakdown

Action Capability

Autonomy

Adaptation

State & Memory

Safety

How agenticness works →

ThumbGate

Agenticness15/36·Guided Assistant

Agent Infrastructure

ThumbGate sits in front of coding-agent tool calls and blocks risky repeats before they run. It turns thumbs-up and thumbs-down feedback into reusable rules, with local use for individuals and paid options for dashboards, sync, and team visibility.

Chrome Extension

Code Execution

Integrations

BuyWhere Product Catalog API

Agenticness6/36·Guided Assistant

Agent Infrastructure

BuyWhere gives developers a normalized product catalog API for Singapore and Southeast Asia. It helps AI agents search, compare, and route commerce queries without scraping storefronts.

Free Tier

API

Chrome Extension

Runloop AI

Agenticness15/36·Adaptive Collaborator

Agent Infrastructure

Runloop AI provides sandboxed devboxes for agent workflows, including turn-based interaction through GitHub pull requests. It’s aimed at developers building coding agents that need to execute commands, keep state across turns, and respond to reviewer comments.

API

Integrations

B2B

Anyscale

Agenticness10/36·Guided Assistant

Agent Infrastructure

Anyscale is a fully managed Ray platform that removes the infrastructure work from building and deploying AI applications. It helps teams run Ray jobs, services, and workflows with autoscaling, monitoring, and API-driven cluster management.

Paid

API

B2B

Stay in the loop

Get the weekly agentic AI briefing

New tools, top picks, and trends — delivered every Thursday.

Composio

Ask about Composio

About

Dimension Breakdown

Categories

Ask about Composio

Related Tools

Get the weekly agentic AI briefing