Skip to main content
Glama

Get BBQ Cooking Guidance

bbq_get_cooking_guidance
Read-onlyIdempotent

Plan BBQ cooks by getting target temperatures, time estimates, and expert tips for specific proteins based on weight, desired doneness, and cooking method.

Instructions

Get comprehensive cooking guidance for a specific protein including target temperatures, time estimates, and tips.

This is the primary tool for planning a cook. It provides:

  • Target internal temperature based on desired doneness

  • Pull temperature (accounting for carryover)

  • Estimated cook time based on weight and method

  • Timeline for when to start if serving time is specified

  • Stall warnings for large cuts

  • Resting instructions

  • Pro tips for the specific protein

Args:

  • protein_type: Type of meat (e.g., 'beef_brisket', 'pork_shoulder', 'chicken_whole')

  • weight_pounds: Weight in pounds (e.g., 12.5)

  • target_doneness: Desired doneness level (optional, uses recommended if not specified)

  • cook_method: Cooking method (optional, uses recommended if not specified)

  • serving_time: Target serving time in ISO 8601 format (optional)

  • response_format: 'markdown' or 'json'

Examples:

  • "How should I cook a 14 lb brisket?" -> protein_type='beef_brisket', weight_pounds=14

  • "I want to serve pulled pork at 6pm" -> protein_type='pork_butt', serving_time='2024-12-25T18:00:00'

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
protein_typeYesType of protein being cooked (e.g., 'beef_brisket', 'pork_shoulder', 'chicken_whole')
weight_poundsYesWeight of the protein in pounds (e.g., 12.5 for a 12.5 lb brisket)
target_donenessNoDesired doneness level. If not specified, will use the recommended doneness for the protein type.
cook_methodNoCooking method to use. If not specified, will recommend the best method for this protein.
serving_timeNoTarget serving time in ISO 8601 format (e.g., '2024-12-25T18:00:00'). Used to calculate when to start cooking.
response_formatNoOutput format: 'markdown' for human-readable or 'json' for structured datamarkdown

Implementation Reference

  • Primary handler function for bbq_get_cooking_guidance tool. Computes cooking guidance using protein profile, target temps, cook time estimates, and optional timeline. Supports markdown and JSON output formats.
    async (params: GetCookingGuidanceInput) => {
      try {
        const profile = getProteinProfile(params.protein_type);
        const cookMethod = params.cook_method || getRecommendedCookMethod(params.protein_type);
        const { targetTemp, pullTemp, doneness } = getTargetTemperature(
          params.protein_type,
          params.target_doneness
        );
        const estimate = estimateCookTime(
          params.protein_type,
          params.weight_pounds,
          cookMethod
        );
    
        let startTimeInfo: { startTime: Date; restTime: number; bufferMinutes: number } | undefined;
        if (params.serving_time) {
          const servingDate = new Date(params.serving_time);
          startTimeInfo = calculateStartTime(
            params.protein_type,
            params.weight_pounds,
            cookMethod,
            servingDate
          );
        }
    
        if (params.response_format === "json") {
          const output = {
            protein: {
              type: params.protein_type,
              displayName: profile.displayName,
              category: profile.category,
              weightPounds: params.weight_pounds,
            },
            temperatures: {
              targetTemp,
              pullTemp,
              carryover: profile.carryoverDegrees,
              usdaSafeMin: profile.usdaSafeTemp,
            },
            doneness: {
              level: doneness,
              displayName: DONENESS_INFO[doneness].displayName,
              description: DONENESS_INFO[doneness].description,
            },
            cookMethod: {
              method: cookMethod,
              displayName: COOK_METHOD_INFO[cookMethod].displayName,
              tempRange: COOK_METHOD_INFO[cookMethod].tempRange,
            },
            timeEstimate: {
              totalMinutes: estimate.totalMinutes,
              hoursAndMinutes: estimate.hoursAndMinutes,
              confidence: estimate.confidence,
              estimatedDoneTime: estimate.estimatedDoneTime.toISOString(),
            },
            timeline: startTimeInfo
              ? {
                  startTime: startTimeInfo.startTime.toISOString(),
                  restTimeMinutes: startTimeInfo.restTime,
                  bufferMinutes: startTimeInfo.bufferMinutes,
                }
              : null,
            rest: {
              required: profile.requiresRest,
              minutes: profile.restTimeMinutes,
            },
            stall: profile.stallRange
              ? {
                  expectedRange: profile.stallRange,
                  warning: "Temperature may plateau for 2-4 hours in this range",
                }
              : null,
            tips: profile.tips,
            assumptions: estimate.assumptions,
            warnings: estimate.warnings,
          };
    
          return {
            content: [{ type: "text", text: JSON.stringify(output, null, 2) }],
            structuredContent: output,
          };
        }
    
        const markdown = formatCookingGuidanceMarkdown(
          profile,
          params.weight_pounds,
          targetTemp,
          pullTemp,
          doneness,
          cookMethod,
          estimate,
          startTimeInfo
        );
    
        return {
          content: [{ type: "text", text: markdown }],
        };
      } catch (error) {
        const message = error instanceof Error ? error.message : "Unknown error occurred";
        return {
          isError: true,
          content: [{ type: "text", text: `Error getting cooking guidance: ${message}` }],
        };
      }
    }
  • Zod schema defining input parameters and validation for the bbq_get_cooking_guidance tool, including protein_type, weight, doneness, method, serving_time.
    export const GetCookingGuidanceSchema = z
      .object({
        protein_type: ProteinTypeSchema.describe(
          "Type of protein being cooked (e.g., 'beef_brisket', 'pork_shoulder', 'chicken_whole')"
        ),
        weight_pounds: z
          .number()
          .positive()
          .max(50)
          .describe("Weight of the protein in pounds (e.g., 12.5 for a 12.5 lb brisket)"),
        target_doneness: DonenessLevelSchema.optional().describe(
          "Desired doneness level. If not specified, will use the recommended doneness for the protein type."
        ),
        cook_method: CookMethodSchema.optional().describe(
          "Cooking method to use. If not specified, will recommend the best method for this protein."
        ),
        serving_time: z
          .string()
          .optional()
          .describe(
            "Target serving time in ISO 8601 format (e.g., '2024-12-25T18:00:00'). Used to calculate when to start cooking."
          ),
        response_format: ResponseFormatSchema.describe("Output format: 'markdown' for human-readable or 'json' for structured data"),
      })
      .strict();
  • src/index.ts:122-261 (registration)
    Registration of bbq_get_cooking_guidance tool in main index.ts entrypoint, linking schema and handler with metadata and annotations.
    server.registerTool(
      "bbq_get_cooking_guidance",
      {
        title: "Get BBQ Cooking Guidance",
        description: `Get comprehensive cooking guidance for a specific protein including target temperatures, time estimates, and tips.
    
    This is the primary tool for planning a cook. It provides:
    - Target internal temperature based on desired doneness
    - Pull temperature (accounting for carryover)
    - Estimated cook time based on weight and method
    - Timeline for when to start if serving time is specified
    - Stall warnings for large cuts
    - Resting instructions
    - Pro tips for the specific protein
    
    Args:
      - protein_type: Type of meat (e.g., 'beef_brisket', 'pork_shoulder', 'chicken_whole')
      - weight_pounds: Weight in pounds (e.g., 12.5)
      - target_doneness: Desired doneness level (optional, uses recommended if not specified)
      - cook_method: Cooking method (optional, uses recommended if not specified)
      - serving_time: Target serving time in ISO 8601 format (optional)
      - response_format: 'markdown' or 'json'
    
    Examples:
      - "How should I cook a 14 lb brisket?" -> protein_type='beef_brisket', weight_pounds=14
      - "I want to serve pulled pork at 6pm" -> protein_type='pork_butt', serving_time='2024-12-25T18:00:00'`,
        inputSchema: GetCookingGuidanceSchema,
        annotations: {
          readOnlyHint: true,
          destructiveHint: false,
          idempotentHint: true,
          openWorldHint: false,
        },
      },
      async (params: GetCookingGuidanceInput) => {
        try {
          const profile = getProteinProfile(params.protein_type);
          const cookMethod = params.cook_method || getRecommendedCookMethod(params.protein_type);
          const { targetTemp, pullTemp, doneness } = getTargetTemperature(
            params.protein_type,
            params.target_doneness
          );
          const estimate = estimateCookTime(
            params.protein_type,
            params.weight_pounds,
            cookMethod
          );
    
          let startTimeInfo: { startTime: Date; restTime: number; bufferMinutes: number } | undefined;
          if (params.serving_time) {
            const servingDate = new Date(params.serving_time);
            startTimeInfo = calculateStartTime(
              params.protein_type,
              params.weight_pounds,
              cookMethod,
              servingDate
            );
          }
    
          if (params.response_format === "json") {
            const output = {
              protein: {
                type: params.protein_type,
                displayName: profile.displayName,
                category: profile.category,
                weightPounds: params.weight_pounds,
              },
              temperatures: {
                targetTemp,
                pullTemp,
                carryover: profile.carryoverDegrees,
                usdaSafeMin: profile.usdaSafeTemp,
              },
              doneness: {
                level: doneness,
                displayName: DONENESS_INFO[doneness].displayName,
                description: DONENESS_INFO[doneness].description,
              },
              cookMethod: {
                method: cookMethod,
                displayName: COOK_METHOD_INFO[cookMethod].displayName,
                tempRange: COOK_METHOD_INFO[cookMethod].tempRange,
              },
              timeEstimate: {
                totalMinutes: estimate.totalMinutes,
                hoursAndMinutes: estimate.hoursAndMinutes,
                confidence: estimate.confidence,
                estimatedDoneTime: estimate.estimatedDoneTime.toISOString(),
              },
              timeline: startTimeInfo
                ? {
                    startTime: startTimeInfo.startTime.toISOString(),
                    restTimeMinutes: startTimeInfo.restTime,
                    bufferMinutes: startTimeInfo.bufferMinutes,
                  }
                : null,
              rest: {
                required: profile.requiresRest,
                minutes: profile.restTimeMinutes,
              },
              stall: profile.stallRange
                ? {
                    expectedRange: profile.stallRange,
                    warning: "Temperature may plateau for 2-4 hours in this range",
                  }
                : null,
              tips: profile.tips,
              assumptions: estimate.assumptions,
              warnings: estimate.warnings,
            };
    
            return {
              content: [{ type: "text", text: JSON.stringify(output, null, 2) }],
              structuredContent: output,
            };
          }
    
          const markdown = formatCookingGuidanceMarkdown(
            profile,
            params.weight_pounds,
            targetTemp,
            pullTemp,
            doneness,
            cookMethod,
            estimate,
            startTimeInfo
          );
    
          return {
            content: [{ type: "text", text: markdown }],
          };
        } catch (error) {
          const message = error instanceof Error ? error.message : "Unknown error occurred";
          return {
            isError: true,
            content: [{ type: "text", text: `Error getting cooking guidance: ${message}` }],
          };
        }
      }
    );
  • Alternative handler implementation for Smithery deployment with inline Zod schema. Logic mirrors main handler.
    server.tool(
      "bbq_get_cooking_guidance",
      "Get comprehensive cooking guidance for a protein",
      {
        protein_type: z.string().describe("Type of protein (e.g., 'beef_brisket')"),
        weight_pounds: z.number().positive().describe("Weight in pounds"),
        target_doneness: z.string().optional().describe("Target doneness level"),
        cook_method: z.string().optional().describe("Cooking method"),
        serving_time: z.string().optional().describe("Target serving time (ISO 8601)"),
      },
      async ({ protein_type, weight_pounds, target_doneness, cook_method, serving_time }) => {
        try {
          const profile = getProteinProfile(protein_type as ProteinType);
          const method = (cook_method as CookMethod) || getRecommendedCookMethod(protein_type as ProteinType);
          const { targetTemp, pullTemp, doneness } = getTargetTemperature(
            protein_type as ProteinType,
            target_doneness as DonenessLevel | undefined
          );
          const timeEstimate = estimateCookTime(protein_type as ProteinType, weight_pounds, method);
    
          let startTimeInfo: { startTime: Date; restTime: number; bufferMinutes: number } | undefined;
          if (serving_time) {
            const result = calculateStartTime(
              protein_type as ProteinType,
              weight_pounds,
              method,
              new Date(serving_time)
            );
            startTimeInfo = {
              startTime: result.startTime,
              restTime: result.restTime,
              bufferMinutes: result.bufferMinutes,
            };
          }
    
          const markdown = formatCookingGuidanceMarkdown(
            profile,
            weight_pounds,
            targetTemp,
            pullTemp,
            doneness,
            method,
            timeEstimate,
            startTimeInfo
          );
    
          return { content: [{ type: "text", text: markdown }] };
        } catch (error) {
          const message = error instanceof Error ? error.message : "Unknown error";
          return { content: [{ type: "text", text: `Error: ${message}` }], isError: true };
        }
      }
  • Key helper function getTargetTemperature used by the handler to compute target and pull temperatures based on protein and doneness.
    export function getTargetTemperature(
      proteinType: ProteinType,
      doneness?: DonenessLevel
    ): { targetTemp: number; pullTemp: number; doneness: DonenessLevel } {
      const profile = getProteinProfile(proteinType);
    
      // Determine the doneness to use
      let actualDoneness: DonenessLevel;
      if (doneness && profile.donenessTemps[doneness] !== undefined) {
        actualDoneness = doneness;
      } else {
        // Use the first available doneness (most common/recommended)
        const availableDoneness = Object.keys(profile.donenessTemps) as DonenessLevel[];
        actualDoneness = availableDoneness[0];
      }
    
      const targetTemp = profile.donenessTemps[actualDoneness] ?? profile.usdaSafeTemp;
      const pullTemp = targetTemp - profile.carryoverDegrees;
    
      return { targetTemp, pullTemp, doneness: actualDoneness };
    }
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=false. The description adds valuable behavioral context beyond annotations: it details the comprehensive output structure (target temperatures, time estimates, tips, stall warnings, resting instructions, etc.), specifies that it provides timeline calculations if serving_time is given, and mentions optional parameter defaults. This enriches the agent's understanding of what to expect from the tool's behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured and appropriately sized. It starts with a clear purpose statement, then details the output components, lists parameters with examples, and includes practical examples. Every sentence adds value, though the 'Args' section slightly duplicates schema information. It's front-loaded with the core purpose and comprehensive nature.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (6 parameters, comprehensive output), no output schema, and rich annotations, the description is largely complete. It thoroughly explains the tool's purpose, usage context, and behavioral output. The main gap is the lack of explicit output structure details (e.g., format of returned guidance), but the description compensates by listing output components. It's sufficient for an agent to understand and invoke the tool effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already fully documents all parameters. The description adds minimal value beyond the schema: it lists parameters in the 'Args' section but repeats information already in the schema descriptions. The examples provide some contextual usage but don't add significant semantic depth. Baseline 3 is appropriate when schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Get comprehensive cooking guidance for a specific protein including target temperatures, time estimates, and tips.' It specifies the verb ('Get comprehensive cooking guidance') and resource ('for a specific protein'), and distinguishes itself from siblings like bbq_estimate_cook_time and bbq_get_cooking_tips by offering a broader, integrated planning function.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit usage guidance: 'This is the primary tool for planning a cook.' It distinguishes when to use this tool versus alternatives by positioning it as the comprehensive planning tool, implying that more specialized tools (e.g., bbq_estimate_cook_time, bbq_get_target_temperature) are for specific aspects rather than full planning.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/jweingardt12/bbq-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server