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

Annotations already mark the tool as read-only and idempotent, so the description's job is lighter. It adds useful behavioral context: results are newest-first, include an unread count, and are per-person because channel acceptance can differ even within the same team. This goes beyond what the schema or annotations reveal.

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 two short sentences with no wasted words. The first sentence front-loads the resource, ordering, and unread count; the second explains why the data is per-person. Both sentences earn their place.

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?

For a low-complexity tool with one optional parameter and an output schema, the description is largely sufficient. The main gaps are that it does not explicitly name whose inbox is returned (current user is implied) and does not point to related sibling tools, but these are minor given the available structured metadata.

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 100% and the only parameter, unread_only, is fully described in the schema. The description does not add meaningful parameter semantics beyond mentioning unread count, so the baseline 3 is appropriate.

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 identifies a specific resource — 'this person's in-app alert deliveries' — and gives two key characteristics: ordering ('newest first') and an unread count. It stops short of a perfect 5 because it never explicitly contrasts with siblings like list_alert_firings or mark_inbox_read, though the resource is fairly distinct.

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?

There is no explicit guidance about when to use get_inbox versus alternatives such as mark_inbox_read or list_alert_firings. The 'per person' note hints that this tool is user-scoped rather than team-wide, but no exclusions or alternative conditions are stated.

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