Tool descriptions are the primary lever

When the model picks the wrong tool, the description is almost always the fix.

4 min read · Lesson 3 of 10 in this domain

When an agent picks the wrong tool, the reflex is to add error handling or a confirmation step. Both are reactive — they clean up after a decision that was already made badly. The description is what the model actually reads when deciding, so it is where the problem is caused and where it should be fixed. The most effective descriptions are prescriptive about when to call, not just what the tool does, and they say explicitly what the tool is not for when a sibling tool could be confused with it.

• Tool and parameter descriptions are the main mechanism the model uses to decide what to call and how to format inputs. They act before generation.
• For confusable tools (delete_file vs archive_file), expand both descriptions to state purpose, boundaries, and explicit negative constraints — what the tool is not for.
• Be prescriptive about when to call, not just what the tool does: "Call this when the user asks about current prices or recent events."
• For input-format problems, clear per-parameter descriptions beat complex regex. Regex validates but does not guide — the model still guesses, then gets told it guessed wrong.
• A confirmation gate inside a destructive tool is worthwhile protection, but it does not correct the upstream selection error.

Source: Claude Docs — Tool use overview · Independent study aid, not affiliated with or endorsed by Anthropic.