prepare_batch_delete_emails

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

With no annotations, the description discloses key behaviors: returns per-email tokens, supports selective confirmation, errors on non-existent IDs, and tokens expire after 5 minutes. It also makes clear the prepare step doesn't execute deletion, which is crucial.

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?

Four sentences, each with essential info: purpose, output, follow-up, error handling, and expiry. No wasted words, and the most important detail (prepare to delete) is front-loaded.

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?

The description fully covers the two-phase workflow, constraints, error conditions, and token lifecycle, making the tool self-contained even without an output schema. It tells the agent exactly what to expect and how to proceed.

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 schema already provides 100% coverage for email_ids, including range, item type, and source examples. The description adds context about per-email tokens but no additional syntax or format details, so 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?

The description clearly states it prepares deletion of multiple emails (up to 50), distinguishing it from single-email prepare_delete_email and batch-move alternatives. The verb 'prepare' + resource 'multiple emails' gives specific 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?

It gives clear context: use when you want to delete multiple emails and selectively confirm via tokens. It explicitly directs to confirm_batch_operation for execution, but doesn't contrast with single-delete or batch-move tools. The 50-email limit and error behavior imply appropriate usage.

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