generate_email_draft

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

The description includes '[mutation]' hinting at state change and mentions AI usage, adding some transparency beyond the schema. However, it does not disclose whether the draft is saved, returned, or how it is stored. Without annotations, the description should provide more details on side effects and output behavior.

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 very short and front-loaded, using two sentences to convey the core purpose. No unnecessary information. Ideal for quick scanning. Slightly more structure (e.g., specifying output) could be added without bloat, but it remains concise.

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 simple 2-parameter tool without output schema, the description covers the main function and AI aspect. However, it does not explain what the tool returns (e.g., draft text or confirmation) or how to access the generated draft. This leaves some contextual gaps for the agent.

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?

The input schema already provides full coverage (100%) with descriptions for both 'thread_id' and 'instructions'. The tool's description adds no further semantic value beyond what the schema already states. Baseline score of 3 is appropriate.

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 action ('Generar borrador de email con IA'), the resource (email draft), and the method (using AI). It distinguishes the tool from siblings like 'send_email_reply' (which sends) and 'list_email_drafts' (which lists), making the purpose unambiguous.

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 generating a draft but does not explicitly state when to use this tool vs alternatives. For example, it doesn't mention not to use it for sending or that it creates a draft that can be later sent. More explicit guidance on when to choose this over 'send_email_reply' or 'get_smart_reply_suggestions' would improve clarity.

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