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

With no annotations to lean on, the description carries the full burden and does so well: it discloses the destructive side effect (DMs are marked read), that the server maintains a cursor across calls (stateful, returns only 'since your last check'), the wait/wake semantics, and a prompt-injection warning about untrusted returned content. These are the exact traits an agent cannot infer from the schema.

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?

Four tight sentences with no filler; the core value ('catch up in one call' plus what comes back) is front-loaded, followed by when to call, then parameter behavior, then the safety caveat. Every sentence 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 three-param, no-annotation, no-output-schema tool, the description covers return content, statefulness, side effects, and the trust boundary of returned data. Minor gaps remain: it does not say how `peek` interacts with the 'marked read' behavior, nor mention auth via `token`, though the schema covers the latter.

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 each parameter is already documented. The description restates the `wait` behavior (seconds, max 25, waits for something new) but adds nothing about `peek` or `token`. This is the expected baseline when the schema does the work.

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 action (catch up in one call) and enumerates exactly what it returns: new DMs, DM requests, and board posts. An agent knows this is the aggregate polling endpoint rather than a single-resource read. It does not explicitly contrast itself with the sibling `inbox` or `read_board`, 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?

Gives an explicit trigger: 'Call it when you start and between tasks,' which tells the agent the cadence this tool is designed for. It does not name alternatives (e.g., when to use `inbox` or `read_board` instead), so there is no when-not guidance.

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