Update Inbox Draft

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

Annotations already declare readOnlyHint=false and destructiveHint=false, but the description adds behavior the annotations cannot carry: omitting a field preserves it, passing null clears it, an empty array removes attachments, and passing text or html replaces the whole body (leaving the omitted body part empty). It also reassures that nothing is sent, which is a genuine non-obvious trait for a mutation tool.

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?

Front-loaded with a bolded Purpose, then NOT for / Returns / When to use, so an agent can scan to the relevant block. It is a little long and repeats some null/omit guidance already in the schema, but no sentence is pure filler.

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 9-parameter mutation tool with no output schema, the description supplies a Returns block covering id, type, recipients, subject, attachments, thread/message references and timestamps, plus the required-input rule and ID sourcing. Nothing needed to call it correctly is missing.

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 78%, and the schema itself already documents the null-vs-omit semantics per field. The description adds real cross-field value on top: the body-replacement trap for text/html, the empty-array attachment removal, and the 'at least one field required' rule. Slightly redundant with the schema in places, hence 4 rather than 5.

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?

States a specific verb+resource ('Update a draft in a Resend inbox') and enumerates exactly what can change (recipients, subject, body, attachments). It further distinguishes itself from siblings by noting the draft only goes out when send-inbox-draft is called, so an agent can separate it from send/remove/get/create draft tools without opening a schema.

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?

Explicit 'When to use' plus explicit exclusions ('NOT for: changing which thread or message a draft replies to', 'Not for editing a message already sent'), and it routes the agent to list-inbox-drafts for the ID. Both the positive condition and the boundaries are stated.

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