save_document

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

With no annotations, the description carries the full burden. It does disclose a meaningful behavioral constraint — content must be HTML, not Markdown — which prevents malformed input. But it omits what happens on success, whether an existing title is overwritten, and any permission/return behavior for this write operation.

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?

A single front-loaded sentence states the action, followed by the critical format constraint and a concrete example. No filler; every element earns its place.

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?

For a save tool with no annotations and no output schema, the description covers the input format well but is silent on the write's side effects (overwrite semantics, return value). Adequate but with clear gaps for a mutation operation.

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 100%, so both parameters are already documented in the schema. The description restates the HTML format for content but adds no syntax or validation detail beyond what the schema's own description provides. Baseline 3 is appropriate.

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?

States a specific verb+resource: '保存新文档到 TextView' (save a NEW document). The word '新' implicitly distinguishes it from the sibling update_document, but no alternative is named explicitly. An agent can grasp the core action without opening the schema.

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 word '新' (new) implies this is for creating rather than updating, giving weak when-to-use guidance. However, no alternatives (update_document, save_memo) are named and no exclusions are stated. Usage is left largely to inference.

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