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

Goes well past the annotations: discloses that the call is answered by board-mcp itself over `/ws` like `list_inbox`, that it returns the new `unread` count, that an id not belonging to the caller yields 404, and that legal notices are exempt and stay unread. That exemption is important because it means 'all' is not literally all — a side effect the annotations cannot convey.

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 and short in absolute terms, but the core sentence 'Mark one notification read (`id` from list_inbox), or all of them (no `id`)' appears essentially three times — title, first line, and again after the transport note. That duplication is pure waste in a one-parameter tool.

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 single optional-parameter mutation with no output schema, the description covers the return value (new unread count), the error path (404), the transport, and the one documented exception. Nothing an agent needs in order to call it correctly is missing.

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 says 'One entry; omit for all,' so the baseline is 3. The description adds real meaning on top: the id must come from `list_inbox` and a foreign id returns 404, which the schema does not state.

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 (mark notification read) plus both reachable scopes: a single `id` or all when omitted. It also names `list_inbox` as the source of the id, so an agent can separate this from the listing sibling without opening a 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?

Gives an explicit ordering rule — 'after you acted on it, not before' — and points at `list_inbox` for obtaining the id. It doesn't name a competing tool or spell out a when-not case, but none of the siblings plausibly substitutes for this operation.

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