message_draft

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

The description discloses a key behavioral guarantee beyond the annotations: no external side effect until a human confirms. This is valuable safety-relevant context. It does not contradict readOnlyHint=false because the tool may still perform local work or prepare a draft, but the key external behavior is clarified.

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 communicats purpose and the most important behavior with zero waste. Every word 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?

The description is adequate for a simple preview tool and clearly states the safety guarantee. However, it does not describe the return value or what the agent should expect after invoking it, and param-level guidance is absent. With no output schema, this leaves a modest gap.

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%, and the description adds no additional meaning for to, subject, or body. The parameter names are self-explanatory, but no format, constraints, or examples are provided, leaving the description to carry the burden it does not shoulder.

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 uses a specific verb ('Preview') with a clear resource ('Gmail draft') and adds a decisive scope qualifier: nothing reaches Gmail until human confirmation. This distinguishes it from send-oriented sibling tools like message_send_propose, even without naming an alternative.

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 implies usage: use this to preview before anything is sent or reaches Gmail. However, it does not explicitly state when to prefer this over alternatives, nor mention any exclusions or preconditions.

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