Skip to main content
Glama

下载真实生成结果

pavo_download_task_results
Idempotent

Downloads completed task results to an absolute directory, returning paths, byte counts, and SHA. Reuses SHA-verified files, avoids overwriting others, and retries failed downloads only.

Instructions

从原生成功任务的真实结果下载至绝对目录,逐项返回路径、字节数和SHA。复用经回执核SHA的已有文件,不覆盖其他文件;失败只重试下载,不重新生成。

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "task_id": "<task_id>",
      "output_dir": "<output_dir>"
    },
    "name": "pavo_download_task_results"
  }
}

Input Schema

NameRequiredDescriptionDefault
task_idYes
output_dirYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.1

TDQS

A3.7/5.0
Behavior4/5

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

The annotations already establish idempotentHint=true, destructiveHint=false and readOnlyHint=false, and the description explains the mechanics that produce those traits: existing files with a receipt-verified SHA are reused, other files are not overwritten, and a failure retries only the download without regenerating. That is useful behavior beyond the annotations, though it says nothing about permissions, disk-space or error surfacing.

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?

Two dense sentences lead with the action and destination, then the reuse/no-overwrite/retry guarantees. Every clause carries information; the only cost is that the guarantees are packed into one semicolon-linked sentence, which reads tightly but is still parseable.

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?

With an output schema present, the description need not explain returned path/byte/SHA values, and it correctly focuses on the write semantics and retry policy of a file-writing tool. What remains unstated are failure modes such as an unwritable or missing output_dir and whether the target directory must already exist.

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 0%, so the description has to carry the parameters, and it adds two real constraints: output_dir must be an absolute directory and task_id must refer to a natively successful task. It adds no format detail for task_id (e.g. native vs script task identifiers), leaving a gap for a tool whose sibling set spans both conventions.

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 gives a specific verb (download) and resource (a natively successful task's real results) plus the destination (an absolute directory), so the operation is unambiguous. It still does not differentiate this tool from nearest siblings such as pavo_sync_task_result or pavo_list_artifacts, which an agent must resolve by other means.

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?

'从原生成功任务' implies a precondition (the task must have succeeded natively) and the note about retrying only the download implies behavior on failure, which together hint at when this is appropriate. However, the description never states when to prefer this over siblings like pavo_sync_task_result or what to do if the task is not successful; it only implies those boundaries.

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