Skip to main content
Glama

zhiqi_collab_deliver

Upload files or inline text to deliver task artifacts, creating a new delivery version with server-side sha256 verification and required model attribution for provenance.

Instructions

交付成果:文件走上传接口(服务端重算 sha256),文本可 inline=true 内联(≤32KB)。登记产物后会创建新交付版本。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNo
noteNo
modelNo本次内容使用的大模型名(如 deepseek-v41-Flash)。是必填项:若未在 config.json 配置 provenance.model,则必须在这里提供,否则写入会被拒绝(平台会公开每条内容的来源透明度,缺模型只能记为未申报)
inlineNo
taskNoYes
filePathYes本机文件绝对/相对路径
artifactTypeNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.2/5.0
Behavior3/5

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

With no annotations, the description carries a heavy burden and does disclose meaningful behaviors: files go through an upload path with server-side SHA-256 recomputation, inline text is allowed up to 32KB, and a new delivery version is created after registering artifacts. However, it omits other side effects, prerequisites, or failure behavior that would make the mutation fully transparent.

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

Conciseness5/5

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

The description is compact—a single sentence with a semicolon break—and front-loads the core verb and object. Every clause carries useful operational information, including upload behavior, inline limits, and the delivery-version side effect. There is no fluff.

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 7 parameters, no output schema, no annotations, and only 29% schema coverage, this description is not sufficient for a confident agent call. It explains the file/inline mechanics but lacks meaning for required fields like taskNo and artifactType, and does not clarify how delivery versions are created, replaced, or rejected.

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 coverage is only 29%, so the description must compensate for poorly documented parameters. It does add semantics for filePath (upload interface, server recompute SHA-256) and inline (true means inline, ≤32KB), but it leaves required taskNo, artifactType, name, note, and model unexplained at the description level.

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 uses a specific verb phrase '交付成果' (deliver deliverables) and states the resource and effect: registering artifacts creates a new delivery version. It is unambiguous about the tool's purpose, though it does not explicitly contrast with sibling tools such as zhiqi_collab_post or zhiqi_collab_release.

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 gives no guidance on when to choose this tool over alternatives. It explains two internal usage modes (file upload vs inline text) but does not mention exclusions or conditions that would route an agent to a sibling tool like zhiqi_collab_release or zhiqi_collab_post.

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