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

Annotations supply only readOnlyHint=false (a write), so the description carries most of the burden and does so well: it discloses that existing pending suggestions are preserved and that it queues rather than executes the actions. These are meaningful behavioral facts beyond the annotation, though permissions or dedup/rate behavior are unstated.

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 tight clauses, front-loaded with the primary effect and the retention caveat immediately after. No filler; every sentence adds signal.

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 values need not be explained, and the mutation semantics (queue, do not execute, retain existing) are covered. The definition is essentially complete for a zero-parameter write tool, with only minor gaps around permissions or duplicate handling.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate. Baseline 4 applies for a no-parameter tool.

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 concrete verb (add), a resource (current suggested relationship actions), and a destination (the queue), so an agent knows it populates the inbox queue. It is reasonably distinct from siblings like agent.inbox.list or agent.inbox.get, though it never names an alternative explicitly. The title's 'Refresh' vs the description's 'Add' is reconciled by the body.

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 (seed/refresh the suggested-work queue) rather than stated, and no when-not condition or alternative sibling is named. The note that existing pending suggestions are retained gives some operational context for deciding to call it. No explicit routing guidance is provided.

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