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

Annotations already cover the safety profile (readOnlyHint, destructiveHint false, closed world), so the bar is lower; the description still adds real value by naming what is excluded (scan contents, forwarding addresses, identity artifacts, storage paths), asserting idempotency, and describing the pagination cursor. The 'every prerequisite stated above' phrasing is vague but not contradictory.

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 purpose and exclusions are front-loaded and useful, but the tail carries boilerplate ('plus every prerequisite stated above', the elongated confirmation-boundary sentence listing unrelated operation types) that dilutes rather than informs.

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?

With no output schema, listing returned fields is genuinely helpful, and the negative list of what is never returned is a good touch. But the parameters are entirely undocumented and no cursor-following behavior is explained, leaving the agent short on how to actually page through mail.

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?

Five parameters with 0% schema description coverage, yet the description never explains limit, statuses, companyId, beforeReceivedAt, or the _corply_context object. 'Bounded page' and 'opaque pagination cursor' gesture at pagination but give no syntactic help, so the description fails to compensate for the coverage gap.

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 opening sentence gives a specific verb and resource ('List a bounded page of canonical envelope-level mail metadata for an active Corply mailbox') and enumerates the returned fields, so the operation is unmistakable. It never distinguishes itself from the many nearby siblings (get_corply_mail, get_mail_item, list_inbox_messages, list_company_inboxes), which is the only gap.

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?

Prerequisites are stated (authenticated active company access) and the confirmation-boundary sentence implies this is a free read needing no extra approval. However, there is no when-to-use-this-vs-alternatives guidance at all, leaving the agent to guess between list_mail, get_corply_mail and list_inbox_messages.

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