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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, so the bar is lower. The description still adds real value: result ordering (newest first), the fields returned (sender, subject, short preview), and the constraint that company-managed teammates have no mailbox — a scope caveat absent from the annotations.

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?

Two sentences, no filler, with the core list scope and ordering front-loaded and the edge-case caveat second. Every clause earns its place.

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 the description correctly specifies the return fields, which is a plus. But the pagination contract (limit plus the 'before' cursor and how they interact) is undocumented in both schema and description, and that is a meaningful gap for a newest-first listing tool.

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 25% (just 'before'), leaving limit, company and teammate undocumented. The description's 'newest first' hints that 'before' pages backwards in time, but it never explains the limit ceiling or the required company/teammate UUIDs, so it fails to compensate for the low coverage.

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?

Names a specific verb (List) and resource (mail received by a Summer-managed teammate) and enumerates the returned fields (sender, subject, preview) plus ordering (newest first). It scopes out company-managed teammates, but never references the sibling summer_teammates_mailbox_get, so an agent must infer how listing differs from fetching a single message.

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 line 'Company-managed teammates have no mailbox in Summer' is a genuine when-not signal that saves a wasted call. However, there is no positive guidance on when to reach for this versus summer_teammates_mailbox_get, and no mention of paging behavior, so usage is only implied.

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