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

Annotations already mark this as read-only, idempotent, and non-destructive. The description adds significant non-obvious context: the scopes required (agent.inbox.read, plus agent.read for sample activity), the agent-scoped bearer key requirement, the semantics of a receipt not being proof of worker compliance, and the fact that rollout/approval/authorization settings are shared with REST. This substantially exceeds annotation-only transparency.

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 description is long but front-loaded with deprecation and replacement, then states the function, parameter, scopes, key requirements, and caveats. Some repetition exists ('needs agent.inbox.read' appears twice), but every sentence carries important operational information, making it dense though not bloated.

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?

The description covers the deprecation status, replacement tool, functional behavior, relevant parameters, required scopes, key type restrictions, and behavioral caveats. With an output schema present, the agent can determine return shape; the only minor omission is an explanation of the `limit` parameter, but this is less critical given the strong context otherwise.

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 schema description coverage at 0%, the description must explain parameters. It explains `item_id` as 'filters one item' and that it needs `agent.inbox.read`, but it never mentions `limit`, its default, maximum, or how it affects paging. So it adds partial value but leaves one parameter semantically undocumented.

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 'Deprecated: use get_inbound_activity' and then explicitly states the tool reads 'current authorized inbox retrieval receipts and agent-reported outcomes' via a specific endpoint. This clearly identifies the verb, resource, and even the alternative, distinguishing it from sibling tools like get_agent_inbox_context.

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 explicitly tells the agent to use get_inbound_activity instead, and states this endpoint is 'still served unchanged during the alias window,' providing a clear condition for when this tool should still be called. It also warns against substituting other keys or mail APIs after denial, which is actionable guidance.

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