List outbox

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

With no annotations, the description must carry the full behavioral burden, and it does add real value: it discloses ordering (scheduled first in send order, then the terminal states) and explains that failed entries carry an error code and that outcome_unknown means the send was interrupted and delivery is indeterminate. However, it is silent on pagination/limit behavior, on whether filtering by status preserves the described ordering, and on permission or auth requirements, which are meaningful gaps for an unannotated tool.

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 tight sentences: the content of the list and its ordering come first, then the semantic edge case, then the sibling pointer. No filler, and the most decision-relevant fact (ordering) is front-loaded.

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?

There is no output schema, so the description must convey return shape; it does describe ordering and the error-code/outcome_unknown field, which is the most important part. But for a zero-required-parameter listing tool it leaves out pagination behavior and how the status filter reshapes results, so it is adequate rather than complete.

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% — just connection_id is documented in the schema. The description explains the status categories but never frames them as a filter, never mentions the limit parameter or its 1–200 cap, and omits the "sending" state that appears in the enum. An agent must open the schema and still guess how limit and status interact with the stated ordering.

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 opens with a concrete resource and scope ("Messages you queued") and enumerates the included states (scheduled, sent, failed, canceled), so an agent can tell it is an outbound-queue listing rather than an inbox read or a search. It also names the sibling message_status for single-message lookups, which sharpens the boundary. The only weakness is that the listing verb is implied rather than stated and the contrast with read_inbox is left implicit.

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 an explicit routing rule: use message_status to follow one message, implying this tool is for browsing the whole queue. It does not say when to prefer it over read_inbox or search, nor whether filters should be used to narrow results, so the guidance is clear but not exhaustive.

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