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

Annotations already declare the safety profile (not read-only, non-destructive, idempotent), so the bar is lower; the description still adds real behavior beyond them, notably that 'kept' removes the item from the unread count and retains it for a year, and that acting via the suggested tool implicitly resolves. It does not cover auth/permission requirements or partial-failure behavior.

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, front-loaded with the core operation and followed by the auto-resolution caveat. The parenthetical glosses are dense but each earns its place by disambiguating an enum value.

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 an output schema present, return values need not be explained, and the description covers purpose, all four action modes, and the redundant-resolve rule. Missing only minor operational details such as the 100-item batch cap and any error/permission behavior, so it is near-complete for a 3-parameter 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 coverage is only 33% (only idempotency_key is documented in-schema), so the description must carry weight and does: it defines the semantics of all four `action` enum values in prose, which is the critical decision parameter. It does not mention the item_ids batch limit (maxItems 100) or the idempotency_key itself, but the enum gloss substantially compensates.

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 ('Marks') and resource ('inbox items'), then enumerates the four action modes (seen, resolved, dismissed, kept) with a gloss for each. An agent can immediately distinguish this mutation from read siblings like get_inbox or from leave_in_inbox/withdraw_item 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?

Explains what each action means (resolved = you acted on them, dismissed = hide without acting, kept = envelopes only) and adds a routing rule: acting with the suggested tool already resolves the item, so a manual resolve is redundant. It stops short of naming alternative siblings or stating exclusions, so it is clear context without full when-not coverage.

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