check

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

Annotations already disclose readOnlyHint=false, openWorldHint=true, and non-idempotency, and the description is consistent with that state-mutating profile by explicitly stating that it advances this machine's cursor. 'Never resends messages' adds a valuable non-obvious guarantee about repeat behavior. What is missing is what happens when the wait times out or returns nothing.

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 compact clauses with the core action and the cursor side-effect front-loaded, and no filler. The terseness of 'wait for the previous task' is slightly ambiguous, 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?

With an output schema present, the description need not explain return values, and with all parameters optional and fully documented, the remaining burden is behavioral. Cursor advancement and non-resend semantics cover the important risks for a polling tool; the gap is only timeout/empty-result behavior.

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 both the agent and wait_seconds parameters are already fully documented in the schema, including the 0-means-snapshot case. The description adds only the notion of waiting for a task, which does not extend parameter meaning beyond the schema. Baseline 3 applies.

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 supplies the meaning the vague name 'check' lacks: it reads new replies, waits on the previous task, and advances this machine's cursor. The non-resend guarantee further pins down that only unseen messages come back. It stops short of distinguishing itself from the siblings ask, interrupt, and list, so an agent still has to infer which one to pick.

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?

'use after running or an unconfirmed send' is a concrete triggering condition, which is more than most tools offer. However, no exclusion or alternative is named, so the boundary against 'ask' or 'list' is left implicit.

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