Skip to main content
Glama
Tencent

Tencent Cloud COS MCP Server

Official
by Tencent

createDocToPdfJob

Converts documents to PDF by processing specified object paths in Tencent Cloud Object Storage (COS) using the MCP protocol, enabling file transformation without manual coding.

Instructions

创建文档转 pdf 处理任务

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
objectKeyYes对象在存储桶里的路径

Implementation Reference

  • src/server.ts:532-550 (registration)
    Registration of the MCP tool 'createDocToPdfJob' with input schema and handler wrapper that calls CIDocService.createDocToPdfJobs
    server.tool(
      'createDocToPdfJob',
      '创建文档转 pdf 处理任务',
      {
        objectKey: z.string().describe('对象在存储桶里的路径'),
      },
      async ({ objectKey }) => {
        const res = await CIDocInstance.createDocToPdfJobs(objectKey);
        return {
          content: [
            {
              type: 'text',
              text: JSON.stringify(res.data, null, 2),
            },
          ],
          isError: !res.isSuccess,
        };
      },
    );
  • Core handler logic for creating document to PDF job: constructs XML request to Tencent COS CI, submits job, polls status up to 10 times using describeDocProcessJob
    async createDocToPdfJobs(objectKey: string) {
      try {
        var host = this.bucket + '.ci.' + this.region + '.myqcloud.com/doc_jobs';
        var url = 'https://' + host;
        const lastDotIndex = objectKey.lastIndexOf('.');
        const base =
          lastDotIndex === -1 ? objectKey : objectKey.substring(0, lastDotIndex);
    
        const now = new Date();
        const formattedDate = [
          now.getFullYear(),
          String(now.getMonth() + 1).padStart(2, '0'), // 月份补零
          String(now.getDate()).padStart(2, '0'), // 日期补零
        ].join('');
    
        const outPutObject = `${formattedDate}_\${SheetID}/${base}_pdf_${generateCode(6)}.pdf`;
        var body = COS.util.json2xml({
          Request: {
            Tag: 'DocProcess',
            Input: {
              Object: objectKey, // 存在cos里的路径
            },
            Operation: {
              DocProcess: {
                TgtType: 'pdf',
              },
              Output: {
                Bucket: this.bucket,
                Region: this.region,
                Object: outPutObject, // 转码后存到cos的路径
              },
            },
          },
        });
    
        const createResult = await new Promise((resolve, reject) => {
          this.cos.request(
            {
              Key: 'doc_jobs',
              Method: 'POST', // 固定值
              Url: url,
              Body: body,
              ContentType: 'application/xml',
            },
            (error, data) => (error ? reject(error) : resolve(data)),
          );
        });
    
        try {
          const jobsDetail = (createResult as any).Response.JobsDetail;
          const initialCode = jobsDetail.Code;
          const initialState = jobsDetail.State;
    
          if (initialCode == 'Failed') {
            return {
              isSuccess: false,
              message: '文档转pdf失败',
              data: createResult,
            };
          }
          if (initialState == 'Success') {
            return {
              isSuccess: true,
              message: '文档转pdf成功',
              data: createResult,
            };
          } else {
            const jobId = jobsDetail.JobId;
    
            // 开始轮询
            let pollResult: any;
            const maxAttempts = 10;
            const interval = 2000;
            for (let attempt = 0; attempt < maxAttempts; attempt++) {
              // 首次立即执行,后续等待间隔
              if (attempt > 0) await new Promise((r) => setTimeout(r, interval));
              try {
                // 查询任务状态
                const { data: getResult } =
                  await this.describeDocProcessJob(jobId);
                const describeJobsDetail = (getResult as any).Response.JobsDetail;
                const describeJobCode = describeJobsDetail.Code;
                const describeJobState = describeJobsDetail.State;
                // 处理终态
                if (
                  describeJobCode === 'Success' &&
                  describeJobState == 'Success'
                ) {
                  pollResult = getResult;
                  break;
                } else if (describeJobCode === 'Failed') {
                  return {
                    isSuccess: false,
                    message: '文档转换失败',
                    data: getResult,
                  };
                }
              } catch (err) {
                // lastError = err as Error; // 记录错误继续重试
              }
            }
            if (!pollResult) {
              return {
                isSuccess: false,
                message: `轮询超时(${maxAttempts}次未完成)`,
                data: createResult,
              };
            }
            return {
              isSuccess: true,
              message: '文档转码成功',
              data: pollResult,
            };
          }
        } catch (error) {
          return {
            isSuccess: false,
            message: '文档转pdf失败',
            data: error,
          };
        }
      } catch (error) {
        return {
          isSuccess: false,
          message: '文档转pdf失败',
          data: error,
        };
      }
    }
  • Input schema for the tool using Zod: requires objectKey string (path in bucket)
    {
      objectKey: z.string().describe('对象在存储桶里的路径'),
    },
Behavior2/5

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

No annotations are provided, so the description carries the full burden. It states '创建' (create), implying a write/mutation operation, but doesn't disclose behavioral traits such as permissions needed, whether it's asynchronous, rate limits, or what happens on failure. This is a significant gap for a tool that likely initiates a processing job without output schema details.

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 a single, efficient sentence in Chinese that directly states the tool's function without unnecessary words. It's appropriately sized and front-loaded, though it could be slightly more informative. No wasted text, but it borders on under-specification.

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 complexity of creating a processing job with no annotations and no output schema, the description is incomplete. It doesn't explain what the job entails, expected outcomes, error handling, or how to monitor results (e.g., using 'describeDocProcessJob'). For a mutation tool with minimal structured data, more context is needed to guide an AI agent 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?

The input schema has 1 parameter with 100% description coverage ('对象在存储桶里的路径'), so the schema already documents the parameter well. The description adds no additional meaning beyond what the schema provides, such as explaining the objectKey format or constraints. Baseline 3 is appropriate since the schema does the heavy lifting.

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

Purpose3/5

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

The description '创建文档转 pdf 处理任务' clearly states the action (create) and resource (document-to-PDF processing job), which is better than a tautology. However, it doesn't differentiate from siblings like 'createMediaSmartCoverJob' or explain what type of document conversion this handles versus other tools. The purpose is understandable but lacks specificity about scope or differentiation.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing an object in storage), exclusions, or comparisons to sibling tools like 'describeDocProcessJob' for checking job status. Usage is implied from the name but not explicitly stated, leaving gaps for an AI agent.

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

Related 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/Tencent/cos-mcp'

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