---
id: "concept-description-routing-signal"
type: "concept"
source_timestamps: ["09:35:00", "09:45:00", "15:28:00"]
tags: ["routing", "metadata", "best-practices"]
related: ["concept-skill-anatomy", "claim-single-line-description", "quote-where-skills-die", "quote-routing-signal", "contrarian-description-over-instructions", "entity-org-anthropic"]
definition: "The principle that a skill's description field is not just a human-readable label, but the primary mechanism an agent uses to decide whether to invoke the skill."
sources: ["s43-file-format-agreement"]
sourceVaultSlug: "s43-file-format-agreement"
originDay: 43
---
# The Description as a Routing Signal

## Definition

A skill's `description` field is not a human-readable label — it is the primary mechanism an agent uses to decide whether to invoke the skill.

## Where Skills Go to Die

Nate B. Jones identifies the description as *"where most skills go to die"* (see [[quote-where-skills-die]]). Humans tend to write descriptions as vague labels like *"Helps with competitive analysis."* In an agentic workflow this tells the agent *"absolutely nothing useful"* and the skill is silently ignored.

## Description = Routing Signal

From [[quote-routing-signal]]: *"The description becomes a routing signal, not a label. You are basically telling the agent through that little description where it should go in the workflow."*

A highly effective description must include:

- **specific document types** the skill consumes/produces
- **exact trigger phrases** an agent might encounter
- the **expected output format**
- the **scenarios** in which the skill is the right tool

## The Under-Trigger Problem

[[entity-org-anthropic-d43]]'s own guidance is that skills tend to **under-trigger** rather than over-trigger. Therefore descriptions need to be *pushy* and explicit, giving the agent high confidence that invoking this skill is the correct action.

## The 80/20 Rule

The speaker advises spending **80% of your attention** on getting the description right — see also [[contrarian-description-over-instructions]].

## Technical Constraint

Note also [[claim-single-line-description]]: in current Claude implementations, multi-line descriptions silently truncate at the first line, breaking the routing signal.

## Related

- [[concept-orchestrator-pattern]] — orchestrators select sub-agents purely from descriptions
- [[action-single-line-descriptions]] — the concrete formatting fix
