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

Annotations cover the safety profile (readOnlyHint=false, idempotentHint=false, openWorldHint=true), so the description's added value is the stateful disclosure: the returned watchId only works within the same MCP session. That is a genuinely useful behavioral trait not derivable from the schema. It stops short of saying what happens to the watch if the session ends or whether repeated calls for the same address dedupe.

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 with the operation and its return value, followed by workflow routing. Mild redundancy between "Returns a wallet snapshot and watchId" and "Save the returned watchId," but each sentence carries a distinct instruction.

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?

With an output schema present, return values need not be explained, and the description still flags the two key outputs. For a 2-param, non-destructive-but-stateful tool it covers what an agent needs; only edge cases (session expiry, duplicate watches) go unaddressed.

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% — the chain enum with defaults and the address format (EVM 0x... or Solana base58) are already fully documented in the schema. The description adds no parameter-level semantics beyond that, so the baseline 3 applies.

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+resource ("Create a watch on an address") and immediately names its counterpart monitor.watch.diff, so the agent can distinguish the stateful setup tool from the diff tool without opening either schema. Also names the concrete artifact produced (wallet snapshot + watchId).

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?

Explicitly says when to use it ("create the first address snapshot in a stateful watch workflow") and what to do next with the alternative ("call monitor.watch.diff in the same MCP session for later changes"). The sequencing and the session constraint are both spelled out rather than left to inference.

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