email_channel_write

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

Annotations already declare destructiveHint=true and openWorldHint=true, so the safety bar is lower, yet the description adds concrete consequences: delete_domain means 'its inboxes stop working', and send_human_reply transmits real mail. It does not mention permission requirements or whether deletes are reversible, keeping it below a 5.

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 workflow sentence followed by a compact, scannable action table; almost every clause carries information. It is dense and long, but the length is justified by eight distinct actions, with only minor redundancy between the action gloss and its 'Needs' entry.

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 12-param, multi-action mutation tool with no output schema, the definition covers the workflow, the action list, required params per action, and the real-world side effects. Remaining gaps are minor: the settings object contents and the mode/orgId parameters are left to the schema.

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?

With only 50% schema description coverage across 12 parameters, the description compensates well by listing the exact params each action needs ('Needs: domainId, localPart', 'Needs: inboxId', etc.) and explaining localPart/domain formats. Some fields (settings, active, displayName, orgId, mode) are still only implicitly covered, so not a 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-and-resource ('Set up and operate the email channel') and then enumerates all eight actions with a one-line purpose each (create_domain, verify_domain, create_inbox, send_human_reply, etc.). This clearly separates it from the sibling email_channel_read, and an agent can identify which action it needs without opening 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?

Gives an explicit recommended sequence — create_domain → user adds DNS records → verify_domain → create_inbox — which is real procedural guidance, plus the caveat that send_human_reply 'sends a real email'. It does not explicitly state when to prefer email_channel_read over this tool, but the sibling naming makes that inference safe.

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