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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorld, so the baseline is covered. The description still adds real context beyond them: free/no key, the 21:45 UTC daily snapshot and its staleness implication, the excluded campaign address, and the refusal/empty-result behavior. It does not cover pagination or result ordering, but with strong annotation coverage this lands between an adequate 3 and a 4.

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-loaded with purpose, then usage, then explicitly labeled 'Returns:' and edge-case sentences. It is long, but with no output schema the return enumeration earns its space; only the exclusion parenthetical about the campaign address is slightly heavy.

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?

Covers everything needed to call it correctly and interpret results: the return shape (summary, as_provider[], as_client[]), data freshness, malformed-input behavior, and the empty-wallet case. Since no output schema exists, the description properly carries the return-value burden.

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% and the single parameter is already documented as '0x + 40 hex (a provider, an agentWallet, or a client)', so the baseline is 3. The description adds meaning beyond it by naming the three wallet roles in context of the returned as_provider/as_client split and by stating the exact validation outcome for a malformed address.

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 ('List every ERC-8183 escrow job one wallet sells or buys on BNB Chain'), plus the value-add of next step and deadline per job. It explicitly separates itself from bnb_agent_chart and bnb_agent_employment, so an agent can route correctly without opening a 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?

Gives a positive trigger (you hold a provider wallet, agentWallet or client wallet) and the concrete questions it answers: waiting for delivery, in dispute window, pay waiting to be released, expired with refund due. It also gives an explicit exclusion with named alternatives for pre-hire vetting and kernel-wide totals.

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