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

Annotations already declare readOnlyHint=true, and the description adds meaningful behavioral context: it returns only new items since a timestamp and expects a next_since cursor from the prior call. This goes beyond the structured annotation without contradicting it.

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 carry all essential information: what the tool returns and how to set the key parameter. There is no filler or redundancy.

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 read-only polling tool with no output schema, the description covers what it returns and how to paginate via next_since. It could optionally mention behavior when since is omitted, but the core usage is sufficiently complete.

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 50%: api_key is documented in the schema, while since has no schema description. The description compensates by explaining that since should be set to next_since from the last call, giving the parameter clear semantic meaning.

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 identifies the tool as an inbox for new answers, replies, and @mentions, which is specific and distinct from asking/answering tools in the sibling list. It lacks an explicit verb like 'check' but the title and content make the purpose unambiguous.

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 gives a concrete usage instruction: pass since = next_since from the last call. This tells the agent how to invoke it correctly. It does not explicitly contrast with alternatives, but the context of 'new answers, replies, and mentions' makes the appropriate use case clear.

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