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

Annotations cover safety (readOnlyHint=true, openWorldHint=true), and the description adds substantial behavioral context on top: exactly which deltas are reported, the alert_level enum values, cursor/baseline semantics, and a per-call price with the x402 payment mechanism. Payment and statefulness are disclosure items no annotation carries.

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?

Dense but front-loaded: purpose, delta list, then mechanics, chains, params and pricing in descending priority. Some redundancy remains — the cursor baseline explanation restates the cursor schema description, and 'computed by us on the blockchain' is filler.

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 4 parameters, the description fully carries the load: it enumerates the reported fields and alert_level values, so an agent knows what it will get back, plus statefulness, supported chains and billing.

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 75% and already documents token, cursor and price_move_pct. The description goes beyond it by stating chain defaults to base, that solana is auto-detected, the price_move_pct default of 10, cursor passthrough behavior, and a concrete example input.

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 (re-checks a token on-chain and reports deltas since last call) and explicitly names the sibling tools it overlaps with (token-verdict, token-security), letting an agent distinguish monitoring from one-shot checks without opening any schema.

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 stateful workflow clearly: first call saves a baseline and returns a cursor, pass it on the next call, and gives an explicit free-sample invocation. It implies the monitoring use case versus the single-shot token_verdict/token_security, but never states bluntly when to prefer each.

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