Remove Inbox Thread

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

Annotations already declare destructiveHint=true, readOnlyHint=false and openWorldHint=false, yet the description goes well beyond them: a 30-day deletion window, the restore path (update-inbox-thread clears the deadline), and the mandatory confirmation workflow. This is exactly the added context annotations cannot carry.

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 destructive consequence and the confirmation requirement are front-loaded, and each sentence carries a distinct instruction. There is mild redundancy: the confirmation rule is stated once as a 'MUST double-check' and again as 'You may only use this tool if the user explicitly confirms', which could be merged.

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 destructive two-parameter mutation with no output schema, the description supplies everything an agent needs: irreversible-window timing, the recovery tool, the confirmation gate, and the non-destructive alternative. Nothing material 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 description coverage is 100%, including a careful note on inboxId ('Not the Resend receiving address'), so the schema does the heavy lifting. The description only says 'by ID', adding no format or syntax detail beyond what is already structured. Baseline 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?

States a specific verb and resource ('Remove a thread by ID from a Resend inbox') and immediately scopes the blast radius ('moves the whole thread, every message in it included, to the trash folder'). It is clearly distinguishable from sibling remove-inbox-thread-label or remove-inbox-draft, and from update-inbox-thread by the trash semantics.

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?

Explicitly names the when-not and the alternative: 'To get a thread out of the way without trashing it, use update-inbox-thread with folder "archive" instead.' It also imposes a concrete precondition (explicit user confirmation after double-checking) rather than leaving usage to inference.

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