ToolUniverse is a collection of tools, interfaces, and supporting components for building AI systems that perform scientific work. It is for developers creating AI scientist agents that use APIs, databases, machine-learning tools, and domain-specific utilities. The catalogue includes skills, commands, an MCP server, an agent, and a hook for working with the ecosystem.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/mims-harvard/tooluniverse/devtu-optimize-descriptionsnpx skills add mims-harvard/ToolUniverse --skill devtu-optimize-descriptionsgit clone --depth 1 https://github.com/mims-harvard/ToolUniverseWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mims-harvard/tooluniverse/devtu-optimize-descriptions)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/devtu-optimize-descriptions"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/devtu-optimize-descriptions.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00062 | $0.02743 |
| Opus 5 | $0.00031 | $0.01372 |
| Sonnet 5 | $0.00012 | $0.00549 |
| Haiku 4.5 | $0.00006 | $0.00274 |
Grade A, and why
devtu-optimize-descriptions scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- devtu-optimize-descriptions — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ToolUniverse Tool Description Optimization
Optimize tool descriptions in ToolUniverse JSON configuration files to ensure they are clear, complete, and user-friendly.
When to Apply This Skill
Use when:
- Reviewing newly created tool descriptions
- User asks "are these tools easy to understand?"
- Improving existing tool documentation
- Adding new tools to ToolUniverse
- User mentions tool usability, clarity, or documentation
Quick Optimization Checklist
Tool Description Review:
- [ ] Prerequisites stated (packages, API keys, accounts)
- [ ] Critical abbreviations expanded on first use
- [ ] Required vs optional parameters clear
- [ ] Mutually exclusive options numbered/labeled
- [ ] Parameter guidance includes trade-offs
- [ ] Filter syntax shows available fields
- [ ] File size warnings where relevant
- [ ] Examples show realistic usage
Critical Improvements (Fix Immediately)
1. Clarify Required Input Requirements
Problem: Users don't know if they need ONE input or ALL inputs.
Fix: Use "Required: Provide ONE input type" for mutually exclusive options.
// Before
"description": "Process BED regions, motifs, or gene lists..."
// After
"description": "Process genomic data. **Required: Provide ONE input type** - (1) BED regions, (2) DNA motif, or (3) gene list. Analyzes..."
Number the options and use bold for "Required".
2. Add Prerequisites to First Tool
Problem: Users don't know what to install/configure before use.
Fix: Add prerequisites note to first tool in each family.
"description": "Query single-cell data. Prerequisites: Requires 'package-name' (install: pip install tooluniverse[extra]). Returns..."
Include:
- Package installation command
- API key requirements
- Account creation instructions
3. Expand Critical Abbreviations
Problem: New users don't understand technical terms.
Fix: Expand on first use with format: "Abbreviation (Full Name)".
Common abbreviations to expand:
- H5AD → HDF5-based AnnData
- RPM → Reads Per Million
- TSS → Transcription Start Site
- TAD → Topologically Associating Domain
- DRS → Data Repository Service
- API names (MACS2, IUPAC, etc.)
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 348 lines · 62 tokens per session scan A ed4078b13cb6
devtu-optimize-descriptions is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,672 stars, last pushed today), licensed Apache-2.0. It adds 62 tokens to every session and 2,743 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
llm-integration
LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization. Use when implementing tool use, SSE streaming, local model deployment, LoRA/QLoRA fine-tuning, or multi-provider LLM APIs.
agent-engineering-expert
Build LLM agents that use tools safely: tool design, the agent loop, memory, MCP servers, multi-agent orchestration, sandboxing and prompt-injection defence. Use when the user mentions AI agents, tool use or function calling, MCP or Model Context Protocol, autonomous workflows, multi-agent systems, LangChain or…
external-repo-setup
Protocol for GPU agents to clone external GitHub repos, install their dependencies, download pretrained weights, and integrate them as featurizers or models inside a focus-area train.py. Use this when a proposal references a GitHub repo or pretrained checkpoint that is not already present in the focus-area workspace.
multi-agent-focus
Generic skill for self-organizing multi-agent teams that collaborate on an optimization problem. Agents discuss dimensions, form teams, run experiments, and adapt when stagnating. Uses AnonAPI posts for discussion and workspaces for shared state.
agentic-patterns
Fundamental patterns for effective agentic behavior. Teaches decomposition, tool orchestration, error recovery, context management, quality self-assessment, and knowing when to stop. Model-agnostic principles that make any agent more effective regardless of domain. Activate on: "how should I structure this agent"…
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.