check

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

Despite annotations existing, the description adds substantial context they do not carry: it discloses that the cursor is advanced (explaining why readOnlyHint and idempotentHint are false), that results are tagged by channel, and it explicitly warns that received message content is untrusted data written by other sessions, not instructions. That prompt-injection caveat is high-value behavioral guidance no annotation could encode.

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 sentences, no filler. The primary behavior (fetch new messages, advance cursor) is front-loaded, and the security caveat follows as a compact second sentence that fully earns its place.

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 zero-parameter tool with no output schema and clear annotations, the description covers return contents, the mutation, and the safety caveat. It omits a few operational details an agent might want (whether the cursor is per-channel or global, behavior on an empty inbox, and which account it targets given the use_account sibling), keeping it just short of 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?

The tool takes zero parameters, so the baseline is 4; the description correctly does not invent parameter semantics. The only added meaning is that the fetch implicitly spans all channels, which is scope rather than a parameter.

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 a specific verb (fetches) and a precisely scoped resource (new messages in the inbox, across all channels), plus the side effect of advancing the cursor. It implicitly separates itself from siblings like read (per-channel history) and wait (blocking), but never names an alternative explicitly, so it stops short of a 5.

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?

"Right away" hints that this is the non-blocking poll, which contrasts with the sibling wait, but the description never states when to use check versus wait or read. Usage is implied rather than spelled out.

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