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

Goes far beyond the annotations: discloses that the cursor only moves forward and an older point is a no-op (reinforcing idempotentHint with a concrete mechanism), that it returns read_ts plus an unread count, and detailed Ed25519 signing/auth and transport-specific signing rules. The read-only/mutation profile is the only thing annotations carry, and the description still adds substantive 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?

Core behavior is front-loaded in the first sentence and every clause is informative, including the signature requirements. The auth/transport paragraph is dense and long, but it addresses a real prerequisite (signing) rather than padding.

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?

No output schema exists, yet the description names the return values (read_ts, unread count) and covers the auth and transport requirements an agent needs to actually call it. Nothing material 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?

With 100% schema coverage the baseline is 3, but the description adds genuine semantics the schema does not: the three parameters are alternative targeting strategies and 'neither' means newest, plus the forward-only constraint on any given point.

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 ('Move YOUR read cursor in one conversation') and immediately defines the three mutually exclusive ways to target it, which cleanly separates it from read-side siblings like get_conversation or list_conversations.

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?

Explains the invocation modes (message_id, ts, or neither for newest) and the forward-only rule, giving clear context for when this tool applies. It does not name a sibling alternative or an explicit when-not condition, so it stops short of a 5.

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