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

Annotations already flag destructiveHint, openWorldHint, non-idempotent and non-readOnly, but the description adds the crucial non-obvious behavior: a preview phase that sends nothing, and that dry_run wins even when confirm is true. It does not cover error behavior, whether preview accounts for suppressions, or that a sent email is unrecoverable.

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 purpose, then capabilities, then the two-step protocol in imperative form — easy to scan and act on. The version sentence partially duplicates the schema, but overall there is little waste.

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 14-parameter destructive tool with no output schema, the description covers the highest-risk gap: how to avoid an unintended send, including what the preview returns. Remaining gaps (error handling, suppression/preview fidelity, unrecoverability of a confirmed send) are modest for its complexity.

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%, so the baseline is 3. The description reinforces the version 1.0/2.0 and confirm/dry_run interplay, but these meanings are already in the schema property descriptions, so it adds little new semantic detail.

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 ('Send a transactional email via MailerCloud Email API') and enumerates the content types supported. It never names the closely related siblings send_personalized_email or send_test_email, so an agent must infer the boundary itself.

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?

Gives an explicit operating procedure: call without confirm first, show the preview, obtain an explicit yes, then re-call with confirm: true, plus the dry_run override. What's missing is routing guidance against sibling send tools (personalized vs test vs campaign sends).

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