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

Annotations only cover readOnly/openWorld/idempotency, yet the description discloses an unusual amount beyond them: the indexer is unwired, calls refuse with a typed PROVIDER_DOWN and charge nothing, a refusal refunds the debit, an unpaid call returns a payment_required challenge rather than fabricated data, and the current price must be read from tollbridge_pricing. These are exactly the failure/payment behaviors an agent needs. No contradiction with readOnlyHint (paying for a read does not mutate state).

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 payment instruction is duplicated nearly verbatim at the opening and again in the PAID paragraph ('after paying, poll /v1/resolutions/:id until horizon_end' appears twice). The most decision-relevant fact — that the tool is DEFERRED and refuses all calls in v1 — sits mid-paragraph rather than being front-loaded, and the actual purpose arrives after the payment boilerplate.

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?

An output schema exists, so return values need no prose, and the description still covers payment rails, refusal semantics, refunds, and the deferred indexer state — enough for an agent to attempt the call correctly and interpret a refusal. The remaining hole is sibling differentiation against tollbridge_wallet_intelligence.

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 0%, so the description carries the full load. It does well on `payer` — states it is a Base 0x… address, that it can be passed as a tool argument, as an `x-tollbridge-payer` HTTP header, or via an x402 PAYMENT-SIGNATURE. But `address` (the wallet being analyzed) and `chain` get no explanation at all, leaving the central parameter semantics ambiguous.

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 core sentence is specific: a wallet state machine on Base with named states (WATCHING → ACCUMULATING → HIGH_CONVICTION → DISTRIBUTING → EXITING) and named outputs (current state, since, sample adequacy, 30d net flow, first-seen). That is far beyond a tautology. However the purpose is buried behind payment boilerplate and the description never distinguishes this tool from the sibling tollbridge_wallet_intelligence, so an agent must guess which wallet tool to pick.

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 real operational context — pay via x402/credits, then poll /v1/resolutions/:id until horizon_end, and it warns that in v1 calls refuse typed (PROVIDER_DOWN). But it offers no when-to-use-vs-tollbridge_wallet_intelligence routing guidance, which is the main selection decision an agent faces here.

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