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

Annotations only cover safety (readOnly, openWorld, non-destructive), and the description adds substantial behavior: oldest-first ordering, each reply returned exactly once, empty list means nothing yet, typical latency of a few minutes, a 6-checks-per-minute rate limit, and a 24-hour token expiry. This is exactly the operational context an agent needs to poll correctly.

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?

Front-loaded with the core action and token relationship, then layered with dedup, latency, and rate-limit facts. Dense but every clause carries information; only the sentence structure, not the content, is slightly heavy.

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, return shape needn't be described, yet the description still clarifies the incremental/one-shot delivery semantics and the empty-list case. Token lifetime and rate limits round out everything needed to call it safely and repeatedly.

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 schema already describes the token, so the baseline is 3. The description adds real meaning beyond it: the token's origin (returned by ask) and its 24-hour lifetime, which affects how long polling remains valid.

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?

States a specific verb and resource (check for new replies) and ties it to a named sibling, 'ask', which starts the conversation. An agent can distinguish this polling tool from ask without opening either schema.

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?

Clearly sets the context of use: only valid for conversations started with ask, using the token ask returned. It doesn't spell out a when-not case or a polling cadence recommendation beyond the rate limit, but the usage context is unambiguous.

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