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

Annotations already declare readOnly=true, destructive=false, openWorld=true, so the safety profile is covered. The description goes well beyond by disclosing the per-call price, the x402 payment rails and networks, automatic payment by x402 MCP clients, and a free sample — critical cost/auth behavior an agent cannot infer from structured fields.

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-loads purpose and the transaction fields, then covers cursor, pricing, and a sample. Every sentence serves a purpose, though the pricing/sample sentence is dense and could be tightened.

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, the description carries the return-value burden and does so: it names the returned fields (direction, SUI change, status, link, balance) and the cursor handoff, plus the payment requirement. An agent has what it needs to call and interpret this tool.

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%; the schema documents address and cursor, but limit has no description. The description adds genuinely useful cursor semantics (carry it into the next call) but says nothing about what limit controls or its default. Baseline 3 is appropriate given the partial schema coverage.

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 pins down the exact semantics: only new transactions since the last call, with direction, SUI change, status, link and balance. This is clearly distinguishable from siblings like sui_tx (fetch a tx) or sui_address (inspect an address).

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 intended loop pattern ('watch ... in a loop', 'Pass the returned cursor on the next call') and the payment precondition, which is real usage guidance. It does not explicitly name when NOT to use it or contrast with sui_tx/tron_watch, 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.