draft_agent_message

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly states it NEVER sends anything, fetches listing details, and produces text for manual use. This covers the most critical behavior (non-sending) and gives context about the fetch operation. It does not mention potential failure modes or permissions, but for a draft tool this is reasonably transparent.

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 two sentences with zero waste. The main purpose is front-loaded, followed by a concise explanation and a crucial non-sending clarification. Every sentence adds value and there is no redundancy.

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 explains what the tool does and its non-sending nature, which is sufficient for understanding the high-level action. However, it gives no guidance on parameter usage (which is partially addressed in the parameter_semantics score) and does not mention any prerequisites (e.g., needing a valid listing ID). Given the tool has 4 parameters and an output schema, more details on how to structure the request would improve completeness.

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 compensate, but it provides no explanation of any parameter (listing, tone, questions, sender_name). The tool name hints at some semantics, but without any detail an agent cannot know what values to supply, especially for 'tone' or 'questions'. This is a significant gap.

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 specific verb ('Draft'), a resource ('a polite inquiry message to a listing's agent'), and explicitly clarifies it does NOT send. This clearly distinguishes it from sibling tools like get_listing_details or account_status, so an agent can immediately understand its unique purpose.

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 implies when to use it (when you need a drafted message, not a sent one) and the emphasis on 'human action' suggests this is for manual follow-up, but it does not explicitly name alternatives or state 'use X instead when you want to send'. There's no explicit when-not guidance, leaving some inference required.

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