intelligence_draft_response

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

Beyond the annotations (readOnlyHint=true, destructiveHint=false), the description adds crucial behavioral context: 'Returns a SUGGESTED draft for human review - does NOT auto-post' and 'uses the client's LLM.' It also discloses the return shape ({draft, reasoning, sampling_used}), enriching the agent's understanding of what the tool does without modifying Discord state.

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 concise and well-structured, with four sentences organized under bolded headings: Purpose, When to use, Returns. Every sentence adds value, and the use of bold labels makes it fast to parse for an AI agent.

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 4-parameter tool with 75% schema coverage, an output schema, and rich annotations, the description fully covers the tool's purpose, usage scenarios, return value, and the critical non-posting behavior. It provides enough context for correct selection and invocation.

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 75% with useful descriptions for channel_id, intent, and context_message_count, and tone is covered by its enum. The description adds no parameter-specific guidance beyond the schema, so it meets the baseline but does not exceed it. The usage examples indirectly clarify intent, but not enough to raise the score.

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 function with a specific verb and resource: 'Draft a reply to a Discord channel using the client's LLM.' It also explicitly distinguishes itself from sending messages by noting 'Returns a SUGGESTED draft for human review - does NOT auto-post,' which separates it from sibling tools like messages_send.

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 description provides an explicit 'When to use' section with concrete use cases: 'prepare a moderator response, suggest replies for staff, draft outreach.' It also names the alternative action by stating 'The agent decides whether to actually call messages_send after review,' giving clear guidance on when to use this tool versus sending a message directly.

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