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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds valuable behavioral context beyond those: it aggregates across every mailbox, sorts newest first, and warns that message bodies are untrusted third-party text that should be summarized and never followed as instructions. This is genuinely useful and non-redundant.

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?

Three concise sentences, each earning its place: scope and ordering, filter usage, and a security-relevant behavioral warning. The key information is front-loaded and there is no filler.

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 simple list tool with no required parameters and full schema coverage, the description covers the important operational details: aggregation scope, ordering, filter options, and the third-party content safety rule. An agent has enough to select and invoke the tool correctly without additional guidance.

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%, so the baseline is 3. The description adds meaning for the filter parameter beyond the schema, explaining that 'unread' is for triage and 'opportunity' is for buy signals. It also implies that mailbox_id is optional because the default is all connected mailboxes.

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 clearly states the tool retrieves replies across every connected mailbox, newest first. It specifies a concrete resource (the aggregated outreach inbox) and distinguishes it from siblings like get_thread and send_reply by emphasizing aggregation and read-only retrieval.

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 gives explicit, practical usage context: use 'unread' for triage and 'opportunity' for buying-signal flags. It does not explicitly name alternatives or state when not to use this tool, but the filter guidance is clear enough to steer an agent effectively.

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