list_inbound_items

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

Annotations already establish a safe read-only, idempotent profile, but the description adds substantial context beyond them: exact auth requirements (saved-document reads enabled, eligible managed mailbox, both inbound.item.read and inbound.item.scan.read), member vs agent key scoping, no facility/Sandbox/package.read compatibility, non-snapshot results, Retry-After/backoff expectations, and a clear statement that no extraction/retry/signed URL/provider call occurs.

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 deprecation notice and purpose are correctly front-loaded, but the body is ~250+ words of dense prose with several negative-clause disclaimers that repeat the same 'reads only' idea and a trailing aside about member keys vs agent duties (get_mailbox_md) only loosely related to this call. Most sentences carry operational value, but the sheer density and mild redundancy hurt scanability.

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 tool's complexity — deprecation, dual read scopes, key-scoping rules, pagination caps, non-snapshot results — the description covers everything needed to call it correctly. An output schema exists, so return-value detail is appropriately left to it while the description still warns that only metadata/identity, not page text, comes back.

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 100%, so the schema already documents every parameter; the description nonetheless adds real meaning on top — that q is literal AND across NFKC/lowercased metadata and OCR, that terms may match different pages of one item, that received_after is inclusive while received_before is exclusive and both filter intake time not printed dates, and that sender/address terms must go through q.

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?

It states a concrete verb and resource ('Search managed-renter physical mail') and even pins the underlying endpoint and search mode. It explicitly distinguishes itself from its sibling search_inbound_items by declaring the deprecation/alias relationship, so an agent knows exactly which version it is calling.

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?

It gives explicit when-not-to-use guidance ('Deprecated: use search_inbound_items'), a named alternative for follow-up detail (get_inbound_item_sources for selected items), and stop conditions (stop at offset cap; never switch keys/accounts to bypass denial). Routing decisions are fully covered rather than implied.

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