memory_audit_ledger

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

With no annotations provided, the description carries the full burden of behavioral disclosure. Interestingly, the description self-declares 'read-only' which is a helpful honesty signal, but it doesn't say what gets audited, what 'record-integrity findings' entails, whether output could be large, or what the output schema structure is. The output schema exists, so returns aren't a gap, but behavioral specifics are thin.

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 concise sentence that front-loads the read-only safety signal. No wasted words. However, given the tool's abstract nature, a touch more clarifying context (what 'canonical JSONL' refers to) would strengthen usefulness without bloating it.

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?

The tool name suggests a potentially complex audit function with policy and integrity semantics, yet the description offers minimal operational detail about what findings are returned, how to interpret them, or how this relates to sibling memory tools. An output schema exists which covers the return format, but the tool's purpose and operational scope are still 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?

The tool has 0 parameters and 100% schema coverage, so there is no parameter ambiguity. The baseline for zero-parameter tools is 4; the description adds the scoping context (read-only policy and record-integrity) which helps an agent understand what the tool returns without any arguments.

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 description 'Return read-only policy and record-integrity findings for canonical JSONL' states a verb (return) and resource (policy and record-integrity findings), but 'canonical JSONL' is vague and unexplained. It does not distinguish this audit tool from the sibling memory/evidence search tools, and the purpose of an 'audit ledger' isn't clarified beyond a fuzzy 'findings' concept.

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?

No guidance on when to use this tool versus any of the six siblings (memory_fetch_evidence, memory_search_candidates, etc.). It does not state exclusions or alternatives. The 'read-only' framing hints at a safe audit context, but no explicit when/when-not guidance is provided.

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