Tool

# Ground Tool in your agent

## Objective
Use “Tool” precisely in code, documentation, and conversations: A callable operation that lets an agent observe or change a system through an input and output contract.

## Prerequisites
- Inspect how the term is used today in the repository, documentation, and prompts.
- Identify the neighboring notions already named: Skill, Agent, Model Context Protocol (MCP).
- Preserve existing correct usages.

## Working definition
A callable operation that lets an agent observe or change a system through an input and output contract.

## Decisive difference
A tool provides a capability; a skill explains when and how to use it in a procedure.

## Example that counts as Tool
You pass a file path to a file-reading tool. It returns the contents or an error, such as “file not found”. Requesting the read does not prove it succeeded: inspect the returned result.

## Counter-example
A review checklist is not an executable tool; it may be part of a skill.

## Acceptance criteria
- Every use of the term matches the working definition.
- Edge cases are settled with the decisive difference, not by intuition.
- Neighboring notions (Skill, Agent, Model Context Protocol (MCP)) are named with their own term.

## Guardrails
- Show the proposed changes before any external action.
- Do not publish, send, delete, pay for, or change remote state without explicit authorization.
- Preserve unrelated changes and stop if the scope becomes ambiguous.

## Output format
- Outcome or verdict.
- Files or actions involved.
- Checks run and observable evidence.
- Remaining blockers or limitations.

• Requires · The agentic vocabulary already used in the repository and documentation

# Map the neighboring notions

## Objective
Extend the same rigor to the related notions (Skill, Agent, Model Context Protocol (MCP)) so the project vocabulary stays coherent.

## Checks
- List every neighboring notion used without a definition.
- Apply its documented decisive difference.
- Record the still-ambiguous cases for the next entry.

## Guardrails
- Show the proposed changes before any external action.
- Do not publish, send, delete, pay for, or change remote state without explicit authorization.
- Preserve unrelated changes and stop if the scope becomes ambiguous.

## Output format
- Outcome or verdict.
- Files or actions involved.
- Checks run and observable evidence.
- Remaining blockers or limitations.

sha256:1f780f8dd68bad4243fcc92d29ba8098ba71657edc16ad31a412ec4c459ae958

# Fix a mix-up around Tool

## Observed symptom
[DESCRIBE THE SYMPTOM HERE]

## Observable checks
- Compare the disputed usage with the working definition: A callable operation that lets an agent observe or change a system through an input and output contract.
- Apply the decisive difference: A tool provides a capability; a skill explains when and how to use it in a procedure.
- Confront the case with the documented counter-example: A review checklist is not an executable tool; it may be part of a skill.

## Possible causes
- The term is used for a neighboring notion (Skill, Agent, Model Context Protocol (MCP)).
- The observed form (interface, script, service) is confused with the actual behavior.
- An alias (tool call) carries a different meaning in the project.

## Bounded fixes
- Rename or reclassify only the usages that contradict the working definition.
- Document each choice by citing the decisive difference.

## Final verification
- Reread every corrected occurrence against the documented example and counter-example.

## Guardrails
- Show the proposed changes before any external action.
- Do not publish, send, delete, pay for, or change remote state without explicit authorization.
- Preserve unrelated changes and stop if the scope becomes ambiguous.

## Output format
- Outcome or verdict.
- Files or actions involved.
- Checks run and observable evidence.
- Remaining blockers or limitations.

• Requires · The agentic vocabulary already used in the repository and documentation

# Anchor the vocabulary in the project

## Objective
Turn the clarification into a reusable rule so the mix-up does not return.

## Checks
- Add the working definition to the project glossary.
- Link every neighboring term to its own entry.
- Check new documents against the decisive difference.

## Guardrails
- Show the proposed changes before any external action.
- Do not publish, send, delete, pay for, or change remote state without explicit authorization.
- Preserve unrelated changes and stop if the scope becomes ambiguous.

## Output format
- Outcome or verdict.
- Files or actions involved.
- Checks run and observable evidence.
- Remaining blockers or limitations.

sha256:c80377c85c389d8b6b45276f8a59ad0be5b68f3f6ee68b64592cc6c89bb57ce8