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

Annotations declare destructiveHint=true and idempotentHint=true, covering the safety profile. The description adds important behavioral context: extension preserves address and contents, requires an active inbox, and limits prepaid expiry advancement to 30 days. However, it doesn't explain what gets destroyed (despite destructiveHint) or the replay/idempotency semantics beyond the word 'replay'.

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 that are dense but front-load the core purpose. Some redundancy ('Admit or replay' vs 'idempotent') and jargon reduce efficiency slightly, but no wasted sentences.

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 needn't be explained. However, given high parameter complexity (9 params, nested objects, 0% coverage) and destructive semantics, the description omits critical operational details—e.g., what constitutes a valid offer_revision_digest, the role of parent_binding, or how replay detection works. It's adequate but incomplete.

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% and there are 9 parameters (7 required) with no descriptions. The description provides no parameter-level information whatsoever—it doesn't mention offer_id, idempotency_key, parent_binding, or any other field. For a tool with rich, nested input schema and zero documentation, this is a significant gap.

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+resource ('Admit or replay one Agent Inbox Extension invocation') and clarifies scope by noting only inbox.extend envelopes are admitted on this resource. The 'idempotent paid' qualifiers add meaning. It distinguishes itself from siblings like ausca_open_inbox and ausca_prepare_invocation, though the phrase 'host boundary' is jargon that may not be universally clear.

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 description implies usage conditions (settlement authority supplied by host, only inbox.extend offer envelopes) but doesn't explicitly state when to use this vs alternatives like ausca_prepare_invocation or ausca_open_inbox. No when-not-to-use guidance is provided.

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