Draft follow-up message

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

With no annotations, the description carries the full behavioral burden. It explicitly discloses the key behavior: 'Returns draft text only — it does not send anything', indicating no side effects. It also mentions what the draft references, but omits error conditions or prerequisites.

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?

Two sentences, front-loaded with the main action, and both sentences earn their place. The second sentence adds a crucial behavioral boundary without fluff.

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 drafting tool with two parameters and no output schema, the description covers purpose, behavioral scope, and return value ('Returns draft text only'). It does not mention potential errors or prerequisites, but the overall context is sufficiently complete.

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 100%, so baseline is 3. The description adds slight context by mentioning 'role' and 'resume version used', which map to the position parameter and application context, but it doesn't explain parameters beyond the schema.

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 'draft' and resource 'follow-up email for a given application', clearly stating what the tool does. It also distinguishes itself from sending tools by noting 'Returns draft text only — it does not send anything.'

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 gives clear context: use it to draft a follow-up for an application, referencing time since applying, role, and resume version. It explicitly states it does not send, providing an exclusion, though it doesn't name alternative tools like send_gmail_email or draft_gmail_reply.

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