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

Annotations already declare read-only/non-destructive/idempotent/open-world, and the description adds real context beyond them: the snapshot-then-delta pattern, what the deltas contain (liquidity ±%, price ±%, honeypot flips, sell-tax spikes, LP pulls), billing via x402/prepaid header, and the 1-free-call-per-day limit. The snapshot/watchId retention is arguably a state write that sits awkwardly beside readOnlyHint=true, which keeps this from a 5.

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?

Purpose and the two-call pattern are front-loaded, and most sentences carry decision-relevant content (retention, auth, cost). The pricing/'second call is worth more' lines are somewhat promotional padding for an agent that just needs to invoke the tool correctly, costing it a point.

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 fields need not be explained), full schema description coverage, and complete annotations, the description supplies everything else an agent needs: the two-mode invocation flow, retention semantics, auth/cost requirements, and the free tier. Nothing essential to correct invocation 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?

Schema coverage is 100%, so the two parameters are already fully documented in the schema ('Up to 10 token addresses' and 'Or: watchId to re-check an existing list'). The description restates the same mutual-exclusivity and adds the sequencing workflow, but contributes little parameter meaning beyond what structured fields already supply. Baseline 3.

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?

The opening question plus the retention mechanics state a specific verb and resource: diffing up to 10 watchlisted tokens against a prior snapshot. The delta/retention framing inherently distinguishes it from one-shot siblings like token_info or token_risk, but no sibling is named explicitly, so it stops short of the 5 bar.

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?

It gives a clear usage context ('Built for agents holding positions that re-check daily') and an explicit two-call workflow: first call snapshots tokens and returns a watchId, second call returns deltas. It never states when NOT to use it or which sibling to prefer for a one-shot check, so no exclusions are covered.

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