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

Beyond the annotations (idempotent, non-destructive), the description discloses three behaviors the schema cannot: login is required, an AI call may be invoked during drafting, and the tool neither publishes nor grants permissions. The AI-invocation note in particular is non-obvious operational context. It stops short of saying what artifact a draft is (ephemeral state vs. stored record) or how gaps are surfaced.

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?

Three compact clauses with no filler: capability, behavioral caveats, and next step. The information is front-loaded, though the semicolon-chained style and the stray '登录' opener make it read as terse notes rather than a clean lead sentence. Nothing is wasted.

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 two-parameter, non-destructive drafting tool with no output schema, the description supplies the essentials an agent needs: auth requirement, AI involvement, non-publication guarantee, and the save path. The remaining gap is what the draft response contains (the draft itself versus a list of missing items), which is left implicit in '缺项'.

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 must carry the semantics. '按用户文字事实' tells the agent that text is the source material and the three draft kinds echo the kind enum, which covers both parameters at a high level. However, it never explains what distinguishes group from venue from business, or what the 12000-character text should contain, so gaps remain.

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 states a concrete verb and resource: it drafts and organizes group/venue/business material from the user's own text facts, including gap items. It distinguishes itself from the save tools by naming manage_my_community_resource and manage_my_business as the post-verification step. The leading '登录;' token is noise that slightly muddies an otherwise precise statement.

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?

It clearly assigns this tool the drafting phase and routes the agent to manage_my_community_resource or manage_my_business once the draft is verified, giving an explicit alternative with a condition. It does not state the inverse (when not to call it, e.g. when a draft already exists and just needs editing), so it falls short of full when/when-not coverage.

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