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

Annotations already flag destructive, non-idempotent, open-world behavior, and the description reinforces this with high-value context the annotations cannot convey: 'SENDS REAL EMAIL', delivery to real people, staggering over time, and 'It cannot be undone.' This is exactly the behavioral weight a destructive tool needs.

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 short sentences, front-loaded with the most important fact ('SENDS REAL EMAIL') and the irreversible warning trailing. No filler; every clause either warns, instructs, or constrains.

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 two-parameter destructive send tool with full annotation coverage, the description supplies the consequence, the preparatory workflow, and the irreversibility note. No output schema is needed or expected here, and nothing an agent needs to call it safely 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 100% and both parameters are documented in the schema itself (batchId provenance from list_pending_drafts, workspaceId via get_status). The description adds no parameter-level detail beyond that, so the baseline of 3 applies.

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 ('approves every draft still pending in the batch and starts delivering them') with scope made unambiguous. It clearly differentiates from siblings like list_pending_drafts, discard_draft, and skip_batch without requiring the 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 prerequisites are given: show drafts via list_pending_drafts, obtain the person's agreement, and discard unwanted items before calling. The when-not path (discard first) and the alternative surface (list_pending_drafts) are both named.

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