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

With no annotations, the description carries the burden and does so well: it discloses the monotonic forward-only semantic, the no-op behavior for stale seqs, and the error condition for out-of-range acks. The remaining gap is that it never says whose inbox is being acked (per-agent vs. shared) or whether the ack is durable across sessions, which matters for a mutation with zero annotation coverage.

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 short sentences, each carrying distinct information — effect, monotonic rule, error/precondition — with the primary effect front-loaded and no redundant restatement of the name.

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-parameter mutation with no output schema, the description covers effect, ordering, and failure modes adequately. It leaves out the scope of the inbox and whether acking is idempotent across repeated calls with the same seq, but nothing blocks a correct call.

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%, so the baseline is 3, but the description genuinely adds meaning beyond the schema's 'seq of the last event you handled' by clarifying inclusivity ('up to and including'), monotonicity, and the error case when up_to exceeds the newest event.

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 inbox events ... as read') with the inclusive boundary spelled out, and ties the effect to the observable outcome ('so read_inbox stops returning them'), which distinguishes it from the read_inbox sibling.

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 explicit preconditions and exclusions: only ack events you have read, an older seq is a no-op, and an up_to past the newest event is an error. This is a full when/when-not contract rather than a hint.

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