document_preview

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

Annotations already mark readOnlyHint=true, and the description does not contradict this. It adds that the tool performs validation and previews a diff, and that the baseline should come from document_read, which is useful behavioral context beyond the schema. It does not detail failure modes or exact diff semantics, but those are less critical given the read-only annotation.

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?

One compact sentence, purpose first and usage note second, with no filler or repeated schema information. This is a model of concise, front-loaded description.

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?

The description covers the core invocation pattern (pass a document, optionally carry a baseline from document_read), and the output schema reduces the need to describe return values. However, it leaves the meaning of '声明' vague and omits any guidance on the scope parameter, so an agent could misjudge what counts as a valid document. It is minimally complete rather than fully self-sufficient.

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 description coverage is 0%, so the description needed to explain all three parameters, but it only meaningfully clarifies baseline ('携带 document_read 返回的 baseline'). The core document parameter is only implicit in '声明', and scope is never mentioned. This leaves a significant gap for a required parameter.

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?

Description uses specific verbs '校验' and '预览差异' with the document/declaration resource, so an agent can tell this is a validation/preview tool. However, it does not explicitly distinguish itself from related preview siblings like host_preview or document_preview_remove, and the term '声明' is left undefined.

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?

The instruction '编辑时携带 document_read 返回的 baseline' gives explicit context and a concrete prerequisite: when editing, pass the baseline returned by document_read. It does not state when not to use this tool or point to alternatives such as document_apply, so it is clear but not fully exclusive.

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