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

Annotations already declare readOnlyHint, destructiveHint=false, idempotentHint and openWorldHint=false, so "Reads only; nothing here sends or changes anything" largely restates what is already structured. The genuinely additive content is the "one cheap call" cost hint and the note that results carry pointers to deeper tools. Nothing about pagination, result size, or what happens when a category is empty.

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?

A single front-loaded sentence establishes the purpose before the enumeration, and the closing clause clarifies read-only behavior. The six-item enumeration is long but every element is distinct information. Slightly dense for one sentence but nothing is wasted.

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?

No required parameters, no output schema, and a closed-world read-only profile make this a low-complexity tool that the description covers well by listing what appears in the response. What remains unexplained is whether results are grouped per category, truncated, or sorted, but the "anything new?" framing sets expectations adequately.

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 single `days` parameter has a full schema description including default and max, and the rollout of other parameters is zero, so the schema carries the semantics. The description never mentions the lookback window at all, leaving no added meaning beyond the schema. Baseline 3 applies at 100% coverage.

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?

It names a concrete aggregate purpose ("one cheap call for 'anything new?'") and enumerates the six result categories it surfaces: unread packages, due reminders, threads awaiting reply, contact requests, recently accepted contacts, drafts awaiting approval. That enumeration makes it trivially distinguishable from siblings like check_inbox, list_drafts, or list_contacts, which cover only one category each.

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?

It explicitly frames two use cases: a quick "anything new?" check and the natural start of a session. It also routes the agent onward by saying each item comes "with the tool that goes deeper," implying these are the drill-down siblings. It stops short of naming a specific alternative or stating when not to call it.

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