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

Annotations already declare readOnlyHint, openWorldHint and destructiveHint, so safety is covered. The description adds genuinely useful behavior beyond that: it returns immediately, mail typically arrives within seconds, an empty result can be re-checked shortly, and format=html changes what is returned.

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 tight sentences, front-loaded with the core purpose and followed by timing/retry and format behavior. No filler or repetition.

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?

With no output schema, the description carries the burden of describing returns, and it does so partially (newest-first ordering, text vs HTML). The polling/empty-result semantics are covered, though it doesn't detail message fields an agent will encounter.

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 all three parameters are already documented. The description only restates the format=html behavior that the schema enum already explains, adding marginal value over the structured field.

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?

States a specific verb (read) and resource (mail delivered to an inbox from create_inbox), plus ordering (newest first). The example use case (verification code, confirmation link) pins down intent, and it is clearly distinct from sibling create_inbox, which provisions rather than reads.

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?

Gives a concrete scenario for when to use it (retrieving a signup verification code or confirmation link) and explains the retry condition when the inbox is empty. It does not name an alternative tool or state exclusions, but the single-purpose nature makes that gap minor.

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