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

Annotations mark this non-read-only, open-world, non-idempotent, and explicitly not destructive, but say nothing about what actually happens. The description supplies the missing behavior: the report hash is anchored on the Privi blockchain and is tamper-evident, and an organization API key is mandatory. It is consistent with readOnlyHint=false rather than contradicting it, though the cost/latency of anchoring is unstated.

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?

A single front-loaded paragraph: deliverable first, then report contents, then the integrity guarantee, then the auth requirement. The parenthetical list of use cases is dense but each item is a real reason to call it. Nothing is padding, though the sentence is long and could be split.

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?

There is no output schema, so the description carries the burden of telling the agent what comes back, and it does: section-by-section contents plus the blockchain hash that makes the artifact defensible. Auth, time window, and scope filtering are all accounted for, and the report artifact need not be described further.

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 each parameter already carries its own ISO 8601 format hint and omit-behavior (since = all history, until = now, streams = all). The description adds only the loose phrase 'for a period', which it already conveys via the schema. Baseline 3 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 deliverable (an audit-ready compliance report) and enumerates exactly what it contains: actions by type, failures, human approvals, log integrity, on-chain status, findings. That is far more than a restated name. It stops short of distinguishing itself from close siblings like ledger_report_pdf or ledger_read_stream, which an agent may equally plausibly 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?

Gives concrete consumption contexts (SOC 2 evidence, security questionnaires, AI-regulation record keeping) and states a hard prerequisite ('Requires the organization API key'). It never names an alternative tool or a when-not condition, so the agent must infer the boundary with ledger_report_pdf and ledger_read_stream.

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