Skip to main content
Glama
aliyun

Alibaba Cloud FC MCP Server

Official
by aliyun

put-custom-runtime-function

Deploy custom runtime projects to Alibaba Cloud Function Compute with automatic packaging. Updates existing functions and configures runtime settings including commands, ports, and resources.

Instructions

将构建完成的匹配阿里云自定义运行时的工程,部署到函数计算。代码工程不需要手动打包,会自动处理。如果函数已存在,则尝试覆盖并更新目标函数。建议使用该方法前先确认函数是否存在

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
locationYes本地代码工程的根路径,例如/Users/xxx/my-project,不需要打包为zip
functionNameYes函数名称,函数名称在每个region必须是唯一的。
regionNo部署的区域,当前可选的区域是cn-hangzhou, cn-shanghai, cn-beijing, cn-shenzhen, cn-hongkong, ap-southeast-1, ap-southeast-2, ap-southeast-3, ap-southeast-5, ap-northeast-1, eu-central-1, eu-west-1, us-west-1, us-east-1, ap-south-1, me-east-1, cn-chengdu, cn-wulanchabu, cn-guangzhou,默认是cn-hangzhoucn-hangzhou
cpuNo函数的 CPU 规格,单位为 vCPU,为 0.05 vCPU 的倍数。 和 diskSize 必须同时存在, 如果仅仅填写 memorySize, cpu 和 diskSize 可以不填。内存规格(以GB计算)与CPU规格的比例必须在1到4之间,例如内存为1024MB,则CPU必须为0.25到1之间,默认为1
memorySizeNo函数的内存规格,单位为 MB,最小值为128,最大值为 30720。可以选择的内存规格为:128,256,512,1024,2048,4096,8192,16384,32768。默认为2048。内存规格(以GB计算)与CPU规格的比例必须在1到4之间,例如内存为1024MB,则CPU必须为0.25到1之间
customRuntimeConfigYes自定义运行时配置,定义启动命令、参数以及启动的HTTP Server的监听端口
descriptionNo函数的描述,可以描述一下函数的功能。
diskSizeYes磁盘大小,单位是MB,可选值: 512 | 10240
instanceConcurrencyYes单实例多并发数。规定了单个实例可以同时同时被多个请求命中的上限,只对自定义运行时与自定义容器镜像运行时生效。范围为[1, 200]
environmentVariablesNo运行时的环境变量配置
internetAccessNo是否支持从函数实例内访问互联网
logConfigNo日志投递配置。如果配置为auto,则会自动创建SLS日志库并投递日志。如果配置为其他值,则需要配置project和logstore。
vpcConfigNo函数的VPC网络配置。如果配置为auto,则会自动创建VPC、VSwitch与安全组配置。如果配置为其他值,则需要配置vpcId、vSwitchIds与securityGroupId。函数实例会运行在配置的VPC网络中。
roleNo函数运行时的角色配置。授予函数计算所需权限的 RAM 角色,使用场景包含:1. 把函数产生的日志发送到您的日志库中。2. 为函数在执行过程中访问其他云资源生成的临时访问令牌。一般可以设置为aliyunfcdefaultrole。角色ARN为acs:ram::****:role/aliyunfcdefaultrole,只需要输入aliyunfcdefaultrole即可
runtimeNo函数的运行时环境,对于自定义运行时,当前支持debian10,debian11,debian12custom.debian10
timeoutNo函数执行的超时时间,单位为秒,最小 1 秒,默认 3 秒。函数执行超过这个时间后会被终止执行。
layersNo函数计算的层配置,当前会自动为custom.debian10,custom.debian11,custom.debian12添加默认的公共层
tagsNo函数标签的key与value配置

Implementation Reference

  • Core handler function that orchestrates the creation and deployment of a custom runtime function using Alibaba Cloud FC via serverless-devs fc3 component. Downloads code if remote, prepares config, generates s.yaml, and deploys.
    async function createCustomRuntimeFunction(params: any): Promise<CallToolResult> {
        const { location, functionName, region, layers, environmentVariables } = params;
        if (!functionName) {
            return { isError: true, content: [{ type: "text", text: `执行失败,请设置functionName参数` }] };
        }
        const accessKeyId = process.env.ALIBABA_CLOUD_ACCESS_KEY_ID;
        const accessKeySecret = process.env.ALIBABA_CLOUD_ACCESS_KEY_SECRET;
        const stsToken = process.env.ALIBABA_CLOUD_SECURITY_TOKEN || '';
        if (!accessKeyId || !accessKeySecret) {
            return { isError: true, content: [{ type: "text", text: `执行失败,请设置ALIBABA_CLOUD_ACCESS_KEY_ID, ALIBABA_CLOUD_ACCESS_KEY_SECRET, ALIBABA_CLOUD_SECURITY_TOKEN环境变量` }] };
        }
        const accountId = await getAccountId();
        if (!accountId) {
            return { isError: true, content: [{ type: "text", text: `执行失败,获取accountId异常` }] };
        }
        // Prepare layers and env
        const finalLayers = prepareLayers(layers, region);
        const finalEnv = prepareEnvVars(environmentVariables);
        // Build props
        const fc3Props = buildFc3Props(params, accountId, finalLayers, finalEnv);
        // Write yaml
        const tmpYamlDir = prepareTmpDir();
        const yamlPath = writeSYaml(tmpYamlDir, fc3Props);
        // Deploy
        const sconfig: any = {
            AccountID: accountId,
            AccessKeyID: accessKeyId,
            AccessKeySecret: accessKeySecret,
            SecurityToken: stsToken,
        };
        if (stsToken && stsToken.length > 0) {
            sconfig.SecurityToken = stsToken;
        }
        try {
            const result = await deployFunction(functionName, yamlPath, sconfig, fc3Props);
            return { content: [{ type: "text", text: `部署完成。output: ${result}` }] };
        } catch (error: any) {
            return { isError: true, content: [{ type: "text", text: `部署失败:${JSON.stringify(error)}` }] };
        }
    }
  • src/index.ts:374-449 (registration)
    Registration of the 'put-custom-runtime-function' tool with MCP server. Two variants: remote mode (downloads zip from codeUri) and local mode (uses local path). Both delegate to createCustomRuntimeFunction handler.
    if (remoteMode) {
        server.tool(
            "put-custom-runtime-function",
            "提供构建完成的匹配阿里云自定义运行时的zip格式的代码包的可下载链接以及其他函数部署配置,创建函数并部署代码到该函数。如果函数已存在,则尝试覆盖并更新目标函数。建议使用该方法前先确认函数是否存在,如果存在需要确认更新目标函数",
            {
                codeUri: codeUriSchema,
                functionName: functionNameSchema,
                region: regionSchema,
                cpu: cpuSchema.default(1),
                memorySize: memorySizeSchema.default(2048),
                customRuntimeConfig: customRuntimeConfigSchema,
                description: functionDescriptionSchema.optional(),
                diskSize: diskSizeSchema,
                instanceConcurrency: instanceConcurrencySchema,
                environmentVariables: environmentVariablesSchema.default({}),
                internetAccess: internetAccessSchema.default(true),
                logConfig: logConfigSchema.optional(),
                vpcConfig: vpcConfigSchema.optional(),
                role: functionRoleSchema.optional(),
                runtime: customRuntimeSchema.default("custom.debian10"),
                timeout: functionTimeoutSchema.default(3),
                layers: customRuntimeLayersSchema.default([]),
                tags: functionTagSchema.default([]),
            },
            async (args) => {
                const { codeUri } = args;
                if (!codeUri) {
                    return { isError: true, content: [{ type: "text", text: `执行失败,需要指定codeUri参数` }] };
                }
                const location = path.join(os.tmpdir(), `code-${Date.now()}.zip`);
                // download codeUri to location
                await downloadFile(codeUri, location);
    
                if (!fs.existsSync(location)) {
                    return { isError: true, content: [{ type: "text", text: `执行失败,需要指定本地代码工程根路径` }] };
                }
                const nextArgs = {
                    ...args,
                    location,
                }
                return await createCustomRuntimeFunction(nextArgs);
            }
        );
    } else {
        server.tool(
            "put-custom-runtime-function",
            "将构建完成的匹配阿里云自定义运行时的工程,部署到函数计算。代码工程不需要手动打包,会自动处理。如果函数已存在,则尝试覆盖并更新目标函数。建议使用该方法前先确认函数是否存在",
            {
                location: locationSchema,
                functionName: functionNameSchema,
                region: regionSchema,
                cpu: cpuSchema.default(1),
                memorySize: memorySizeSchema.default(2048),
                customRuntimeConfig: customRuntimeConfigSchema,
                description: functionDescriptionSchema.optional(),
                diskSize: diskSizeSchema,
                instanceConcurrency: instanceConcurrencySchema,
                environmentVariables: environmentVariablesSchema.default({}),
                internetAccess: internetAccessSchema.default(true),
                logConfig: logConfigSchema.optional(),
                vpcConfig: vpcConfigSchema.optional(),
                role: functionRoleSchema.optional(),
                runtime: customRuntimeSchema.default("custom.debian10"),
                timeout: functionTimeoutSchema.default(3),
                layers: customRuntimeLayersSchema.default([]),
                tags: functionTagSchema.default([]),
            },
            async (args) => {
                const { location } = args;
                if (!fs.existsSync(location)) {
                    return { isError: true, content: [{ type: "text", text: `执行失败,需要指定本地代码工程根路径` }] };
                }
                return await createCustomRuntimeFunction(args);
            }
        );
    }
  • Zod schema definitions for all tool input parameters, such as customRuntimeConfigSchema, functionNameSchema, regionSchema, etc., imported and used in the tool registration.
    import { z } from "zod";
    
    // region schema
    export const regionSchema = z.enum(['cn-hangzhou', 'cn-shanghai', 'cn-beijing', 'cn-shenzhen', 'cn-hongkong', 'ap-southeast-1', 'ap-southeast-2', 'ap-southeast-3', 'ap-southeast-5', 'ap-northeast-1', 'eu-central-1', 'eu-west-1', 'us-west-1', 'us-east-1', 'ap-south-1', 'me-east-1', 'cn-chengdu', 'cn-wulanchabu', 'cn-guangzhou'])
        .default('cn-hangzhou')
        .describe("部署的区域,当前可选的区域是cn-hangzhou, cn-shanghai, cn-beijing, cn-shenzhen, cn-hongkong, ap-southeast-1, ap-southeast-2, ap-southeast-3, ap-southeast-5, ap-northeast-1, eu-central-1, eu-west-1, us-west-1, us-east-1, ap-south-1, me-east-1, cn-chengdu, cn-wulanchabu, cn-guangzhou,默认是cn-hangzhou");
    
    // equal rule schema
    export const equalRuleSchema = z.object({
        match: z.string().describe("匹配规则"),
        replacement: z.string().describe("替换规则"),
    }).describe("自定义域名完全匹配重写规则配置");
    
    // wildcard rule schema
    export const wildcardRuleSchema = z.object({
        match: z.string().describe("匹配规则"),
        replacement: z.string().describe("替换规则"),
    }).describe("自定义域名通配符重写规则配置");
    
    // regex rule schema
    export const regexRuleSchema = z.object({
        match: z.string().describe("匹配规则"),
        replacement: z.string().describe("替换规则"),
    }).describe("自定义域名正则重写规则配置");
    
    // rewrite config schema
    export const rewriteConfigSchema = z.object({
        equalRules: z.array(equalRuleSchema).describe("精确匹配规则列表"),
        wildcardRules: z.array(wildcardRuleSchema).describe("通配匹配规则列表"),
        regexRules: z.array(regexRuleSchema).describe("正则匹配规则列表"),
    }).describe("重写配置,可以采用精确匹配、通配匹配或正则匹配其中之一");
    
    // path config schema
    export const pathConfigSchema = z.object({
        path: z.string().describe("HTTP协议中的PATH路径,例如/api/,或/api/*"),
        functionName: z.string().describe("路由的目标函数名称"),
        qualifier: z.string().describe("路由的目标函数版本或别名,默认是LATEST").optional(),
        methods: z.array(z.enum(['GET', 'POST', 'PUT', 'DELETE', 'HEAD', 'OPTIONS'])).describe("HTTP方法,可选值为GET, POST, PUT, DELETE, HEAD, OPTIONS").default(['GET', 'POST','PUT', 'DELETE', 'HEAD', 'OPTIONS']),
        rewriteConfig: rewriteConfigSchema.optional(),
    }).describe("自定义域名路由路径配置。");
    
    // route config schema
    export const routeConfigSchema = z.object({
        routes: z.array(pathConfigSchema).describe("路由配置"),
    });
    
    // auth config schema
    export const authConfigSchema = z.object({
        authType: z.enum(['anonymous', 'function']).describe("认证类型,可选值为anonymous, function。anonymous:匿名认证,无需认证。function:函数签名校验认证。默认为匿名校验").optional(),
    }).describe("权限认证配置");
    
    // cert config schema
    export const certConfigSchema = z.object({
        certName: z.string().describe("证书名称"),
        privateKey: z.string().describe("PEM格式证书私钥"),
        certificate: z.string().describe("PEM格式证书内容,必须包含全部的证书内容,包括中间证书"),
    }).describe("证书配置,如果要支持HTTPS协议,则必须要配置证书");
    
    // tls config schema
    export const tlsConfigSchema = z.object({
        minVersion: z.string().describe("TLS版本,可选值为TLSv1.0, TLSv1.1, TLSv1.2, TLSv1.3。默认为TLSv1.2"),
        maxVersion: z.string().describe("TLS版本,可选值为TLSv1.0, TLSv1.1, TLSv1.2, TLSv1.3。默认为TLSv1.2"),
        cipherSuites: z.array(z.string()).describe("TLS密码套件,可选值为TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256, TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384, TLS_ECDHE_RSA_WITH_CHACHA20_POLY1305_SHA256, TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256, TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384, TLS_ECDHE_ECDSA_WITH_CHACHA20_POLY1305_SHA256。默认为TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256, TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384, TLS_ECDHE_RSA_WITH_CHACHA20_POLY1305_SHA256"),
    }).describe("TLS配置,如果要支持HTTPS协议,则必须要配置TLS");
    
    // waf config schema
    export const wafConfigSchema = z.object({
        enable: z.boolean().describe("是否开启WAF"),
    }).describe("Web应用防火墙(WAF)配置");
    
    // log config schema
    export const logConfigSchema = z.union([z.object({
        project: z.string().describe("日志投递的SLS日志项目名称"),
        logstore: z.string().describe("日志投递的SLS日志库名称"),
        logBeginRule: z.enum(["DefaultRegex", "None"]).default("DefaultRegex").describe("日志投递到SLS日志库时的切分规则,可选值为DefaultRegex,表示使用默认的切分规则。启用后,函数计算将按日志分割规则进行切分,切分成多个日志段,并逐条写入日志服务。默认的日志分割规则为 ^.{0,2}\d{4}-\d{2}-\d{2},即匹配符合xxxx-xx-xx格式的日期,其中x代表数字。该规则将按照行首是否带有日期进行切分,例如您的日志行首是2023-10-10,则该日志将被认为是一块日志的首行,首行和接下来连续不带日期的日志将被作为一条日志写入到日志服务。不启用日志分割规则是,默认使用换行符\\n进行切分。"),
        enableInstanceMetrics: z.boolean().default(true).describe("是否开启实例级指标投递,开启后,函数计算会自动将实例级指标投递到SLS日志库。"),
        enableRequestMetrics: z.boolean().default(true).describe("是否开启请求级指标投递,开启后,函数计算会自动将请求级指标投递到SLS日志库。"),
    }), z.enum(["auto"])]).describe("日志投递配置。如果配置为auto,则会自动创建SLS日志库并投递日志。如果配置为其他值,则需要配置project和logstore。")
    
    // vpc config schema
    export const vpcConfigSchema = z.union([z.object({
        vpcId: z.string().describe("VPC的ID"),
        vSwitchIds: z.string().describe("VSwitch的ID"),
        securityGroupId: z.string().describe("安全组ID"),
    }), z.enum(["auto"])]).describe("函数的VPC网络配置。如果配置为auto,则会自动创建VPC、VSwitch与安全组配置。如果配置为其他值,则需要配置vpcId、vSwitchIds与securityGroupId。函数实例会运行在配置的VPC网络中。")
    
    export const protocolSchema = z.enum(['HTTP', 'HTTPS', 'HTTP,HTTPS']).describe("域名路由配置的协议,可选值为HTTP, HTTPS, HTTP,HTTPS。HTTP:仅支持 HTTP 协议。HTTPS:仅支持 HTTPS 协议。HTTP,HTTPS:支持 HTTP 及 HTTPS 协议。");
    
    // update custom domain config schema
    export const updateCustomDomainConfigSchema = z.object({
        protocol: protocolSchema.optional(),
        routeConfig: routeConfigSchema,
        authConfig: authConfigSchema,
        certConfig: certConfigSchema.optional(),
        tlsConfig: tlsConfigSchema.optional(),
        wafConfig: wafConfigSchema.optional(),
    });
    
    export const domainSchema = z.string().describe("域名,例如example.com,域名不能带有'https://'或'http://'等协议内容");
    
    // create custom domain config schema
    export const createCustomDomainConfigSchema = z.object({
        domain: domainSchema,
        protocol: protocolSchema.optional(),
        routeConfig: routeConfigSchema,
        authConfig: authConfigSchema,
        certConfig: certConfigSchema.optional(),
        tlsConfig: tlsConfigSchema.optional(),
        wafConfig: wafConfigSchema.optional(),
    });
    
    // cpu schema
    export const cpuSchema = z.number().describe("函数的 CPU 规格,单位为 vCPU,为 0.05 vCPU 的倍数。 和 diskSize 必须同时存在, 如果仅仅填写 memorySize, cpu 和 diskSize 可以不填。内存规格(以GB计算)与CPU规格的比例必须在1到4之间,例如内存为1024MB,则CPU必须为0.25到1之间,默认为1");
    
    // memory size schema
    export const memorySizeSchema = z.number().describe("函数的内存规格,单位为 MB,最小值为128,最大值为 30720。可以选择的内存规格为:128,256,512,1024,2048,4096,8192,16384,32768。默认为2048。内存规格(以GB计算)与CPU规格的比例必须在1到4之间,例如内存为1024MB,则CPU必须为0.25到1之间");
    
    // function name schema
    export const functionNameSchema = z.string().describe("函数名称,函数名称在每个region必须是唯一的。")
        .regex(/^[a-zA-Z0-9_][a-zA-Z0-9_-]{0,63}$/);
    
    // location schema
    export const locationSchema = z.string().describe("本地代码工程的根路径,例如/Users/xxx/my-project,不需要打包为zip");
    
    export const codeUriSchema = z.string().describe("zip格式代码包下载链接,代码工程必须是已经完成构建后打包的代码工程,且地址必须是免鉴权的地址,例如: https://mybucket.oss-cn-hangzhou.aliyuncs.com/objectName?Expires=1749109495&OSSAccessKeyId=osstmpak&Signature=osstmpsign%3D");
    
    // custom runtime config schema
    export const customRuntimeConfigSchema = z.object({
        command: z.array(z.string()).min(1).describe("自定义运行时启动命令,命令执行的用户是root,执行的目录是/code,例如python3"),
        args: z.array(z.string()).min(1).describe("自定义运行时启动命令参数,例如app.py").optional(),
        port: z.number().describe("自定义运行时中启动的HTTP Server的监听端口,默认为9000").default(9000),
    }).describe("自定义运行时配置,定义启动命令、参数以及启动的HTTP Server的监听端口");
    
    // function description schema
    export const functionDescriptionSchema = z.string().describe("函数的描述,可以描述一下函数的功能。");
    
    export const functionVersionDescriptionSchema = z.string().describe("函数版本的描述,可以描述一下发布的函数版本的功能。");
    
    // disk size schema
    export const diskSizeSchema = z.number().describe("磁盘大小,单位是MB,可选值: 512 | 10240");
    
    // instance concurrency schema
    export const instanceConcurrencySchema = z.number().describe("单实例多并发数。规定了单个实例可以同时同时被多个请求命中的上限,只对自定义运行时与自定义容器镜像运行时生效。范围为[1, 200]");
    
    // environment variables schema
    export const environmentVariablesSchema = z.record(
        z.string().describe("环境变量名称"),
        z.string().describe("环境变量值")
    ).describe("运行时的环境变量配置");
    
    // internet access schema
    export const internetAccessSchema = z.boolean().describe("是否支持从函数实例内访问互联网");
    
    // function role schema
    export const functionRoleSchema = z.string().describe("函数运行时的角色配置。授予函数计算所需权限的 RAM 角色,使用场景包含:1. 把函数产生的日志发送到您的日志库中。2. 为函数在执行过程中访问其他云资源生成的临时访问令牌。一般可以设置为aliyunfcdefaultrole。角色ARN为acs:ram::****:role/aliyunfcdefaultrole,只需要输入aliyunfcdefaultrole即可");
    
    // custom runtime schema
    export const customRuntimeSchema = z.enum(['custom.debian10', 'custom.debian11', 'custom.debian12']).describe("函数的运行时环境,对于自定义运行时,当前支持debian10,debian11,debian12");
    
    // function timeout schema
    export const functionTimeoutSchema = z.number().describe("函数执行的超时时间,单位为秒,最小 1 秒,默认 3 秒。函数执行超过这个时间后会被终止执行。");
    
    // custom runtime layers schema
    export const customRuntimeLayersSchema = z.array(z.string()).describe("函数计算的层配置,当前会自动为custom.debian10,custom.debian11,custom.debian12添加默认的公共层");
    
    // function tag schema
    export const functionTagSchema = z.array(z.object({
        key: z.string().describe("标签名称"),
        value: z.string().describe("标签值")
    })).describe("函数标签的key与value配置"); 
    
    export const listFunctionsPrefixSchema = z.string().describe("函数名称前缀,用于过滤函数列表");
    
    export const listFunctionsNextTokenSchema = z.string().describe("函数列表的下一页token,用于分页查询函数列表。第一页不需要提供");
    
    export const listFunctionVersionsNextTokenSchema = z.string().describe("函数版本列表的下一页token,用于分页查询函数版本列表。第一页不需要提供");
    
    export const listFunctionVersionsLimitSchema = z.number().describe("函数版本列表的返回数量上限,默认50,最大100").min(1).max(100).default(50);
    
    export const listFunctionVersionsDirectionSchema = z.enum(["BACKWARD", "FORWARD"]).describe("函数版本列表的排序方向,BACKWARD表示按版本号降序,FORWARD表示按版本号升序").default("BACKWARD");
    
    export const versionIdSchema = z.string().describe("函数版本ID");
  • Helper function to build the fc3 properties (s.yaml config) for deployment, including defaults for role, customDomain, etc.
    function buildFc3Props(params: any, accountId: string, layers: string[], environmentVariables: Record<string, string>) {
        const { location, functionName, region, cpu, memorySize, customRuntimeConfig, description, diskSize, instanceConcurrency, internetAccess, logConfig, vpcConfig, role, runtime, timeout,  tags } = params;
    
        if (customRuntimeConfig && customRuntimeConfig.args && customRuntimeConfig.args.length === 0) {
            // unset empty args to avoid fc 400 error
            delete customRuntimeConfig.args;
        }
    
        return {
            functionName,
            region,
            cpu,
            memorySize,
            customRuntimeConfig,
            description,
            diskSize,
            instanceConcurrency,
            environmentVariables,
            internetAccess,
            logConfig,
            vpcConfig,
            role: role || `acs:ram::${accountId}:role/aliyunfcdefaultrole`,
            runtime,
            timeout,
            layers,
            tags,
            code: location,
            customDomain: {
                domainName: "auto",
                protocol: "HTTP",
                route: {
                    path: "/*",
                    qualifier: "LATEST",
                }
            }
        };
    }
  • Helper to prepare default official layers for Python, Node.js, Java in custom runtime.
    function prepareLayers(layers: string[], regionID: string): string[] {
        layers.push(`acs:fc:${regionID}:official:layers/Python310/versions/3`);
        layers.push(`acs:fc:${regionID}:official:layers/Nodejs20/versions/3`);
        layers.push(`acs:fc:${regionID}:official:layers/Java21/versions/2`);
        return [...new Set(layers)];
    }
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions the tool '尝试覆盖并更新目标函数' (attempts to overwrite and update) which implies mutation, and notes automatic packaging. However, it lacks critical behavioral details: required permissions, whether deployment is idempotent, error handling for conflicts, rate limits, or what happens to existing function configurations during update. For a complex deployment tool with 18 parameters, this is insufficient.

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 appropriately concise with two sentences. The first sentence states the core purpose and key behavior (automatic packaging). The second provides important usage note about update behavior and pre-check recommendation. Both sentences earn their place without redundancy.

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

Completeness2/5

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

Given the tool's complexity (18 parameters, mutation operation, no output schema, no annotations), the description is inadequate. It doesn't explain what happens on success/failure, return values, error conditions, or operational constraints. While the schema provides parameter documentation, the description fails to provide the holistic context needed for a deployment tool of this complexity.

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 documents all 18 parameters thoroughly. The description adds minimal parameter semantics: it mentions '代码工程不需要手动打包,会自动处理' (code project doesn't need manual packaging, handled automatically) which relates to the 'location' parameter, and implies update behavior for 'functionName'. However, it doesn't provide additional context beyond what's in the schema descriptions. Baseline 3 is appropriate when schema does heavy lifting.

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

Purpose4/5

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

The description clearly states the tool's purpose: '将构建完成的匹配阿里云自定义运行时的工程,部署到函数计算' (deploy a built project matching Alibaba Cloud custom runtime to Function Compute). It specifies the verb ('部署' - deploy) and resource ('函数计算' - Function Compute), and mentions automatic packaging. However, it doesn't explicitly differentiate from sibling tools like 'update-custom-runtime-function' beyond mentioning update behavior.

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

Usage Guidelines3/5

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

The description provides some usage context: '如果函数已存在,则尝试覆盖并更新目标函数' (if the function already exists, it attempts to overwrite and update) and '建议使用该方法前先确认函数是否存在' (suggest confirming if the function exists before using this method). This implies when to use it (for deployment with update capability) but doesn't explicitly contrast with alternatives like 'create' vs 'update' tools or provide clear exclusion criteria.

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/aliyun/alibabacloud-fc-mcp-server'

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