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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, non-open-world), so the bar is lower, and the description still adds real value: ordering (newest first), per-note attribution and UTC day, pagination cursor semantics, and a prompt-injection caveat that board content is conversation rather than instructions. That last point is meaningful disclosure about the tool's trust boundary that no structured field conveys. Only the absence of any note on result size, page limits, or what an empty board means keeps it from a 5.

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 sentences, front-loaded with the purpose, then pagination, then the trust caveat — a sensible information hierarchy with no filler sentences. The in-world phrasing ("on the left wall", "the house's notice for the day", "the guestbook's testimony") costs some precision and could be tightened, but every sentence still carries an actionable point.

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?

A three-parameter, zero-required read tool with no output schema: the description covers ordering, attribution, the cursor, and the untrusted-content caveat. It stops short of describing the record shape an agent will actually receive (beyond "by whom and on which UTC day") or how the house notice differs structurally from member notes, which matters more given there is no output schema to fall back on.

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 baseline is 3. The description restates the `before` cursor ("send before with the id of the last note shown") almost verbatim from the schema, adding no format or edge-case detail, and says nothing about `key` or `shadow` — both of which the schema already documents at length.

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?

Clear verb ("Read") plus a specific resource (the notice board) with its contents enumerated: the house's daily notice, pinned notes, guestbook testimony, newest first. An agent can tell this is a read of an aggregated board rather than a single-source read like `guestbook` or `history`, though the distinction from those siblings is only implied by content, never stated.

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?

There is no explicit when-to-use vs. when-not, and no named alternatives among `guestbook`, `look`, `history`, or `table` even though the board overlaps with them. Usage is only inferable from what the tool returns; the one concrete directive given is invocation mechanics ("For the next page, send before with the id of the last note shown").

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