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

Annotations are all false (not read-only, not idempotent, not destructive), so the description must carry behavioral disclosure. It states that credentials are forwarded once and never stored, which is a security transparency. It also discloses the auto-detection behavior, the failure handling (ask for servers), and the re-authentication use case. This goes beyond the annotations and gives the agent a clear picture of side effects and expectations.

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 description is long but every sentence adds value: purpose, alternative, security note, step-by-step guidance, and special cases. It is well-structured with clear flow, and the key information (user+password first) is front-loaded. No fluff or repetition.

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?

Given the complexity (10 parameters, no output schema, no annotations), the description covers many aspects: purpose, alternative, security, usage flow, and re-auth. However, it does not describe the success return value or what the agent should expect after a successful connection (e.g., connection ID or status). It implies a result by mentioning 'if the result says invalid', but doesn't explain the successful outcome. This is a minor gap for a tool with no output 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?

Schema description coverage is only 40%, so the description must compensate. It does clarify that user+password are the primary required fields and that servers are auto-detected, implying host/port are optional. It provides example server settings for OVH and mentions account_id for re-auth. However, it does not explain imap_encryption, smtp_encryption, or other parameters, leaving their semantics unclear. It partially compensates but not fully.

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 the tool's purpose: connecting a generic IMAP/SMTP mailbox with credentials. It distinguishes itself from the account_connect browser link as an alternative, and specifies it is for generic mailboxes, not Gmail/Outlook. The verb 'connect' and resource 'mailbox' are explicit, and it is differentiated from sibling connect tools like telegram_connect and whatsapp_connect.

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?

The description provides explicit when-to-use guidance: it is the alternative to account_connect when the user prefers typing credentials in chat. It also gives an exclusion: Gmail/Microsoft mailboxes should use Google/Outlook connection instead. It further instructs to start with user+password only and to ask for servers if configuration is invalid, plus how to re-authenticate via account_id. This is clear and actionable.

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