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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), yet the description adds genuinely non-obvious behavior: a hard 50-item page cap, a bounded wait that can legitimately return an empty page plus a continuation cursor, and the credential-placement rule ('supply the lease bearer on the HTTP or MCP transport; never place it in tool arguments'). The auth instruction is exactly the kind of operational detail an agent cannot get from annotations or schema.

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?

Three sentences, zero filler, and the core contract (page size, cursor, bounded wait) is front-loaded before the secondary note about empty pages. The auth constraint is placed last, which is appropriate since it is a caveat rather than the primary purpose.

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?

An output schema exists, so return-value detail is correctly omitted, and the description still flags the surprising empty-page-plus-cursor case. The main remaining gap is the absence of any hint about obtaining the inbox_id or initial cursor, which an agent needs before it can call this tool successfully.

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 0% at the property level, so the description must carry the load. It supplies meaning for 'after' (opaque, inbox-bound, continuation) and 'wait_seconds' (bounded at 30 seconds, may yield an empty page), which is real added value. However, inbox_id is only gestured at via 'For an active inbox', and the description never explains where a valid inbox_id or cursor is obtained.

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 names a concrete verb and resource with scope: 'return at most 50 normalized message summaries after an opaque inbox-bound cursor'. That is far more specific than the title alone and implicitly separates it from single-message siblings like ausca_agent_inbox_read. It stops short of explicitly naming an alternative, so sibling differentiation is inferred rather than stated.

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 phrase 'For an active inbox' establishes a precondition, and the wait semantics imply the polling/streaming use case, but there is no explicit 'use this when / use X instead' routing against ausca_agent_inbox_read, ausca_agent_inbox_status, or the cursor-acquisition tool. Usage is implied rather than prescribed.

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