sui_watch

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

With no annotations, the description carries the full burden and does so well: it discloses the return fields (direction, SUI change, status, link, balance), the stateful cursor contract, a concrete cost ($0.002 USDC per call) and p99 latency (3000ms). What it omits is error/empty behavior (what happens when there are no new transactions) and any auth requirements.

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?

The description is front-loaded with the core behavior before cost/latency metadata, and most clauses carry distinct weight (stream semantics, cursor chaining, output fields, pricing). The leading 'Sui Wallet Watch —' restates the name and is mild overhead, but overall it is dense and efficient.

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 no output schema and no annotations, the description must define the return surface, and it does (direction, SUI change, status, link, balance), plus operational facts (cost, latency). It is nearly complete; the only gap is the undocumented limit parameter and unaddressed empty/error cases.

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 67% (address and cursor are described, limit is not), which puts the baseline near a 3. The description reinforces cursor semantics ('Pass the returned cursor on the next call') but adds nothing about limit's role in bounding results per call, so it does not compensate for the coverage gap.

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 (watch) and resource (Sui address or SuiNS name) and scopes it as an incremental stream ('only new transactions since your last call'). This clearly separates it from sui_address (static lookup), sui_tx (single transaction), and sui_network siblings.

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?

The 'in a loop' framing and 'Pass the returned cursor on the next call' make the polling workflow explicit, so an agent knows this is a repeated-call tool rather than one-shot. However, it never names an alternative (e.g., sui_tx for one-shot lookups) or states when NOT to use it, so it stops short of full routing guidance.

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