{"version":"2.1.248","anchor":"mcp-warns-when-a-tool-description-is-too-long-for-the-model","canonical_anchor":"mcp-warns-when-a-tool-description-is-too-long-for-the-model","heading":"\/mcp warns when a tool description is too long for the model","tier":"use","area":"MCP","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.248\/e\/mcp-warns-when-a-tool-description-is-too-long-for-the-model","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.248","markdown":"### \/mcp warns when a tool description is too long for the model\n\n\/mcp now flags tools whose description is too long for the model to fully receive.\n\n**What**\n\nBrowsing an MCP server's tools in `\/mcp` now shows a dim note under any tool whose description exceeds 2048 characters, telling you the model only receives roughly the first part of it. Useful when a server's tool is being ignored or misused.\n\n**Details**\n\n- The 2048 cap is a constant stored alongside the other MCP protocol constants.\n- The note is assembled from a fixed prefix, the number, and a suffix; no setting hides it.\n\n**Evidence**\n\n`The model receives only about the first`\n\n- Area: MCP\n- Names: `\/mcp`\n- Tier: Use it now\n- Useful: 4\/5\n- Signal: 2\/5"}