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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, covering the safety profile. The description adds valuable behavioral context: it explicitly lists what the tool does NOT receive (message bodies, previews, message ids, customer details, internal notes) and clarifies it reports only the unread count with metadata. This goes beyond the annotations and provides a clear boundary of data exposure. No contradiction exists.

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 sentences long with zero wasted words. The first sentence front-loads the primary purpose and scope, and the second sentence explicitly lists exclusions in a clear, structured manner. Every clause carries meaning, and the description is easily scannable for an agent.

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?

Given the tool has no parameters, an output schema (which likely details return format), and comprehensive annotations, the description is complete. It specifies what the tool reports (unread count), what data it includes (conversation ids, channel, status, unread count, timestamps), and what it excludes (message bodies, previews, etc.). An agent has everything needed to invoke and interpret the result without ambiguity.

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 has zero parameters, so the input schema is empty. The baseline for 0 parameters is 4, and the description adds no parameter-specific semantics because there are none. It does describe the output elements (conversation ids, channel, status, unread count, timestamps) which are relevant for the agent's understanding of the tool's behavior, but since no parameters exist, there is nothing further to document.

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 specific verb ('open') and resource ('metadata-only Supovia inbox') and clearly defines the output: a count of conversations with unread activity. It also enumerates the data elements included and excluded, which differentiates it from sibling tools like list_conversations or open_customer_inbox_conversation without needing to name them.

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 for a lightweight, metadata-only overview of unread activity, and explicitly notes it never passes message bodies or details, suggesting a precursor step for follow-up. However, it does not explicitly state when to prefer this over sibling tools like list_conversations or show_support_overview, nor does it mention any alternatives or exclusion conditions. The context is inferred rather than stated.

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