Unverified60% confidenceOpinionExact time
The progressive disclosure mechanism means that even if an Agent is equipped with hundreds of skills, the actual context usage during runtime may be equivalent to only that of an MCP solution using 3–5 tools.
2
Sources
60%
Confidence
Long-term
Relevance
9/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAn Agent with dozens of tools often needs only two or three of them for a given task; the descriptions of the remaining tools waste tokens and may induce the model to call irrelevant tools.80% similarUnverifiedIn the agent domain, an "expert" is essentially a combination of pre-configured system prompts and specific tool permissions, while a "skill" is closer to the concept of an MCP or traditional API plugin.80% similarUnverifiedA complete Agent typically consists of multiple components including prompts, MCP Server configurations, Skills, and policies, making it a composite entity rather than a single weight file.75% similarUnverifiedProgressive disclosure means that the Agent gradually loads and discloses relevant skill information at runtime according to task needs, rather than exposing all capabilities to the model at once.74% similarUnverifiedWhen the total number of Agent skills is only in the tens, having the model judge directly is simpler and more accurate than a two-stage architecture; the two-stage approach is designed for large-scale scenarios.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/850247API
curl https://kongchang.com/api/v1/knowledge/claims/850247MCP
get_claim(id=850247)