ausca_agent_inbox_messagesReturn at most 50 normalized message summaries after an opaque cursor, optionally waiting up to 30 seconds for a newer message.
| Name | Required | Description | Default |
|---|---|---|---|
| after | No | ||
| inbox_id | Yes | ||
| wait_seconds | No |
| Name | Required | Description | Default |
|---|---|---|---|
| cursor | Yes | ||
| status | Yes | ||
| messages | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety is covered structurally. The description adds value beyond annotations by disclosing the 50-result cap, the opaque-cursor continuation model, and the bounded wait with a 30-second maximum. No contradiction with annotations. Minor gap: it does not state what happens when the wait expires with no new message.
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?
A single dense sentence that front-loads the return behavior and cap, then packs in cursor semantics and wait bounds. Every phrase earns its place with zero filler or repetition of schema/annotation content.
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 an output schema exists, return values need no explanation. Annotations cover the safety profile, and the description covers pagination, result cap, and wait behavior. The only notable gap is undefined timeout semantics (empty list vs. stale results), which is minor for a read-only list 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?
With 0% schema description coverage, the description carries the burden, and it partially compensates: 'after an opaque cursor' clarifies the `after` param and 'waiting up to 30 seconds' maps to `wait_seconds`. However, `inbox_id` is never semantically explained beyond the tool title, and the description does not reinforce the schema's warning that cursors are opaque and must not be constructed or modified.
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 states a specific verb ('Return'), a clear resource (inbound message summaries), and key scoping facts (max 50, after cursor, optional wait). It distinguishes from the sibling ausca_agent_inbox_read by specifying 'summaries' rather than full messages, which implies a list operation, but it never names a sibling or states what it is not.
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?
Usage is implied rather than explicit: 'optionally waiting up to 30 seconds for a newer message' signals a polling/long-poll use case, and listing summaries suggests use when full content is unnecessary. There is no explicit when-to-use statement, no exclusions, and no routing to alternative siblings such as ausca_agent_inbox_read.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct resource and action: inbox list/read/delete/attachment/status, browser connect/close/status, invocation get/cancel/prepare, and offer search/get. Although messages vs read and status could appear similar, the descriptions clearly separate bulk summaries, single-message reads, and lease state. There is no meaningful overlap between any two tools.
All names share the uniform ausca_ lowercase snake_case prefix and are grouped by functional area, making the overall pattern easy to predict. However, the final segment alternates between verb actions (delete, read, connect, cancel, prepare) and noun resources (attachment, messages, status), so it is not a strict verb_noun convention. This is a minor inconsistency rather than chaotic naming.
Thirteen tools cover three distinct functional areas, each with a focused set of operations and no obvious redundancy. This sits comfortably in the ideal 3–15 range and every tool appears necessary for the server's purpose.
The inbox lifecycle is well covered with list/read/attachment/status/delete, and invocation/offer areas support the key operations of search, resolve, prepare, get, and cancel. Creating a browser session or actually submitting an invocation appears intentionally externalized to the transport or offer terms, so there are only minor gaps rather than dead ends.