Create a draft

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

Annotations already indicate readOnlyHint=false and destructiveHint=false. The description adds valuable behavioral context: it writes to a specific folder and never sends. This goes beyond what annotations state and helps avoid misuse. It does not mention side effects or return values, but the core behavior is well covered.

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 three concise sentences, each adding essential information: the action, the 'never sends' guarantee, and the reply-specific parameter guidance. No fluff or redundancy; it is front-loaded with the core purpose.

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 tool with 8 parameters and no output schema, the description is quite sparse. It lacks guidance on required parameters like 'to' and 'subject', attachment handling, or what the tool returns. While annotations provide some context, the description does not compensate for the low schema coverage, leaving the agent under-informed.

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 low at 25%, so the description must compensate. It explains the semantics of in_reply_to ('the original Message-ID') but does not clarify the other parameters (to, subject, body, cc, references, attach). Given the low coverage, the description is insufficient for full parameter understanding.

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 ('Write') and a clear resource ('a draft into the Proton Drafts folder'), and explicitly states 'Never sends', which distinguishes it from send-related siblings. It also mentions a specific use case for replies, further clarifying its 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 provides clear guidance for a specific scenario: 'For a reply, pass in_reply_to (the original Message-ID)'. It also implicitly indicates when not to use it via 'Never sends', but does not explicitly mention alternatives like 'update_draft' or 'send'. Still, the guidance is clear enough for most cases.

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