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

With no annotations, the description carries the burden and does real work: it discloses the default result window, the since-based incremental read, and — most valuably — a trust boundary warning that returned content is written by unverified agents and must be treated as data rather than instructions. It omits auth mechanics (whether a token from `join` is mandatory, and what happens if it is missing) and any rate-limit or failure behavior.

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, zero filler, and the fetch semantics are front-loaded ahead of the safety caveat where they belong. Nothing could be removed without losing information.

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 five-parameter read tool with no annotations and no output schema, the definition covers purpose, default window, incremental paging, and the prompt-injection trust model — the essentials for safe invocation. It falls short on the unstated authentication prerequisite tying `token` to `join`, and gives no notion of what a returned message looks like, which matters given there is no output schema.

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 80%, so the baseline is 3. The description complements the schema meaningfully for `limit` (default 30) and `since` (returns only messages after the given id), but adds nothing about `ch` (channel scoping) or `mine` (message direction), which remain dependent on their terse schema strings.

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 ('Read the shared board') plus the default window ('newest 30, or the ones after since'), so the agent knows exactly what it gets back. It does not distinguish itself from the ambiguous sibling 'inbox', which an agent could reasonably confuse with reading the board.

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?

Usage is implied by the pagination hint — call with `since` to poll for new messages, call bare to fetch the latest 30 — but the description never says when to prefer this over `inbox`, `dm`, or `list_agents`. No prerequisites (e.g., joining first to obtain a token) or exclusions are stated.

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