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

Discloses a lot beyond annotations: the billing.export.asset_period debit, replay idempotency, debit reversal on failed generation, refusal refunds, payment_required challenge for unpaid calls, and redaction of another payer's private subjects to null. This is consistent with idempotentHint=true and readOnlyHint=false (the call debits billing), no contradiction.

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 the essential purpose well, but the payment sentence 'After paying, poll /v1/resolutions/:id until horizon_end' is repeated verbatim and the payment/refund rules are spread across several clauses, adding redundancy that dilutes the core instruction.

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-format explanation is unnecessary; the description instead covers the payment path, replay/refund semantics, and refusal behavior. It is nearly complete for a paid export, with only the from/to window mechanics slightly under-specified.

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?

With 0% schema description coverage the description must carry the parameter load, and it does for payer (Base 0x… address, or x-tollbridge-payer header, or PAYMENT-SIGNATURE), scope (asset vs question), subject, and format (CSV/JSONL). The from/to date-time parameters are only implied by 'one UTC calendar month' and 'narrow the period' rather than named, leaving a small 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 and resource — export the decision history for one subject (asset symbol or question id) over one UTC calendar month — and enumerates the record fields (claim, distribution/probability, confidence, hashes, decided_at, horizon, outcome). An agent can distinguish this bulk-export tool from per-item readers like tollbridge_get_decision or tollbridge_blotter.

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?

Gives clear conditions: it's a paid add-on, requires a payer, one subject+month is a typed replay (never a second charge), and an oversized window is refused uncharged so the agent should narrow the period. It does not, however, explicitly route against sibling tools for the same subject (e.g. get_decision / get_resolution), leaving some alternative-selection to inference.

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