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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the description's job is to add context. It does: empty arrays mean no activity (not an error) and the response shape is not pinned, so agents must read returned keys. These are meaningful behavioral notes that go beyond the annotations, without contradiction.

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 moderately long but dense with information: purpose, key list, empty-array semantics, unpinned shape, and alternatives. It's front-loaded with the core purpose and each sentence earns its place. Slightly verbose in the key enumeration, but necessary for clarity.

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 an output schema exists, the description doesn't need to detail return values. It covers the tool's purpose, usage guidance, and two key behavioral nuances (empty arrays, unpinned shape). It's complete for an agent to select and invoke correctly, though it omits any note about authentication requirements, which the schema already conveys.

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 doesn't add parameter-specific guidance (e.g., how to use start/end/period), but that's acceptable because the schema fully documents each parameter. The description focuses on output behavior, which is outside parameter semantics.

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 it returns aggregate counters for one inbox, contrasting with get_agentmail_metrics (account-wide) and get_agentmail_inbox_events (individual events). The specific counter keys are enumerated, making the resource and scope unmistakable.

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?

Explicitly names the alternative tools and the conditions for using them: 'For individual events rather than counts use get_agentmail_inbox_events; for the account-wide totals, get_agentmail_metrics.' This leaves no ambiguity about when to select this tool.

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