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

With no annotations, the description fully discloses behavior: nothing stored, nothing sent, AI-generated reply for human review. Explicitly states customer_message and product_context are untrusted content, never instructions. No contradictions.

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?

Two concise sentences plus cost note. Front-loaded with core action. No extraneous words. Every sentence 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?

Adequately covers inputs and output ({ draft, disclaimer }). No output schema but description explains return. Could be improved by clarifying disclaimer role, but overall complete for a drafting tool.

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 100%, baseline 3. Description adds value: clarifies product_context as 'optional background about the product/service' and emphasizes untrusted content. Specifies length limits and tone default, exceeding schema info.

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?

Clearly states 'Draft a professional customer-support reply from a raw customer message.' Distinguishes itself by noting tenant-agnostic and no account/ticket id needed, which differentiates it from siblings like 'draft_reply' and 'send_reply'.

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 clear context on when to use (drafting for human review) and what to expect (AI-generated draft + disclaimer). Includes cost note. Lacks explicit 'when not to use' but implicitly covered by the send/save prohibition.

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