Checklist
Give the agent only the tools this job needs
Every extra tool is another verb the system can accidentally conjugate.
When it fits
- An AI workflow can call multiple tools, plugins or functions on the user's behalf.
When to avoid it
- A minimal tool set does not replace input validation, authorization or review of the tool itself.
Checklist
- The task is stated without naming tools first.
- Every exposed tool maps to a required step in that task.
- Unused legacy or trial tools are unavailable to the agent.
- A missing tool produces a visible stop rather than an improvised substitute.
Why it matters
Define the job first, then expose only the tools required to finish that job. Remove abandoned experiments and convenient-but-unused integrations from the agent's reach. Tool selection is a capability boundary, not a menu-design problem.
An example
A research agent that only needs to read repository files should not also inherit issue deletion, release publishing and billing tools.
Check your result
You can justify every available tool with a concrete task step.
Keep this limit in mind
- A minimal tool set does not replace input validation, authorization or review of the tool itself.
Connected ideas
Use beforeStart an agent read-only when writing is not required
Evidence and sources
Supports
OWASP recommends limiting the extensions available to an LLM agent to the minimum needed for its intended operation.
A smaller tool set reduces attack and error surface but does not establish that the remaining tools are safe.
LLM06:2025 Excessive Agency · Minimize extensions