上传图片

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

With no annotations provided, the description carries the full behavioral burden. It discloses the return value (public URL), the anti-leech behavior requiring the absolute URL, and the non-interchangeability of channels. It also warns about the key not being a public address. However, it omits auth requirements and error handling, which are relevant for a tool that uploads data, though the sibling auth tools suggest authentication is expected.

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

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

The description is compact and front-loaded with the core purpose and output. It delivers essential usage instructions and warnings in a few sentences without redundancy. Every sentence adds value, covering purpose, channel selection, and exclusions.

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

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

Given the tool's simplicity (two parameters, no output schema), the description covers the main behavioral expectations: what it does, what it returns, and what to avoid. It lacks explicit auth prerequisites and response format details, but these are partially implied by sibling tools and the clear output statement. Overall, it is sufficiently complete for an agent to invoke correctly in most scenarios.

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

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

Schema coverage is 0%, so the description must compensate. It explains 'kind' (cover vs body) and implies 'path' refers to the local image file, but does not specify path format (absolute/relative), file size limits, or other constraints. While it adds meaning beyond the enum, the path parameter remains underspecified, leaving the agent to infer from the tool name and context.

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

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

The description clearly states the tool's action (upload local image to CSDN image hosting) and its primary output (public URL). It also differentiates from sibling tools by specifying the kind-based channel selection (cover vs body), which is unique among the listed siblings that are all article-related.

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

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

Provides explicit usage guidance: instructs to use the returned absolute URL in article content due to anti-leech, explicitly states not to use it for non-image files, and warns against using the returned key as an image address. It also clarifies that cover and body channels are not interchangeable, giving clear conditions for when to use which.

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