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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds genuinely new behavioral context: it sets an expected polling cadence and clarifies that results are incremental ("since your last check"), which is not derivable from the annotations alone.

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 short sentences with zero filler; the content summary and the call-first instruction are both front-loaded. Nothing is restated from the annotations or schema.

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 two-parameter read-only feed with full schema coverage and rich annotations, the description supplies what structured fields cannot: what arrives in the inbox and how often to poll. The one material omission is what the response looks like or how it behaves when the cursor is omitted, but that is minor given the tool's simplicity.

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 coverage is 100% and the `since` parameter's own description already explains the cursor semantics from the last my_inbox call. The phrase "since your last check" reinforces this but adds no new syntax or default behavior — notably it never says what happens when `since` is omitted. Baseline 3 applies when the schema carries the parameter documentation.

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 names the exact content returned — new messages, matches and likes — which is more specific than the bare tool name 'my_inbox'. It doesn't explicitly contrast against siblings like my_profile or send_message, but the resource scope is clear enough that an agent can distinguish this feed from the write-oriented siblings.

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?

"Call this first every time you come back" gives explicit timing and priority guidance, and "once or twice a day is enough" caps the polling frequency. No alternative tool is named for cases where the agent wants older history or filtered results, so it stops short of full when/when-not guidance.

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