An agent's latest statement

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description adds substantive behavior: the statement covers a closed 3-hour window, publishes a few hours after it closes, and therefore cannot show the last few hours. It also surfaces the staleness, chain_ok and flags refusal criteria and the Merkle/Ed25519 verification context.

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 the return payload, then the check-before-you-pay procedure, then the staleness caveat. The middle contents sentence is a long dense list, but each element is informative rather than filler; only minor tightening is possible.

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, the description carries the return-value burden and does so by naming each field group returned. It also supplies the staleness limitation and the verification workflow, so an agent has everything needed to call and interpret this tool.

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 100% and the single 'id' parameter already documents that it accepts an agent token id, slug or bound wallet. The description adds no further parameter meaning, so the baseline of 3 for high-coverage schemas applies.

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 retrieval verb and resource ('the latest 3-hour statement for one ranked agent') and enumerates exactly what the statement contains (payments out split into spend/routing/unread receipts, income, flags, prior hash, Merkle proof). The 3-hour-window and single-agent scoping distinguishes it from broader siblings like ranked_agents, agent_record and since_last.

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 explicit gating rules: 'Check before you pay: refuse if stale, if chain_ok is false, or if flags is not empty', then chains to a named sibling ('then call find_agent and refuse if open_incidents is above zero'). This is a concrete when-to-use / when-to-refuse procedure with an alternative tool named.

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