memory_audit

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

No annotations are provided, so the description bears full responsibility for disclosing behavioral traits. The description does not indicate whether this operation is read-only, whether it requires special permissions, or what side effects (if any) occur. As a report generator, it is likely safe, but that is not explicitly stated, leaving ambiguity.

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?

Two sentences provide a clear and complete overview. The first sentence states the action, the second specifies what the report shows. No unnecessary words, and the information is front-loaded.

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?

For a tool with no output schema, the description should explain the report's output structure. It mentions what information is included but does not specify the format (e.g., list, summary, counts) or behavior when no results are found. Given the parameter count and lack of annotations, some additional context would improve completeness.

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% with clear descriptions for each parameter. The description adds context about the report content (remembered, forgotten, merged, by agents), which aligns with the parameters. However, it does not add significant new meaning beyond summarizing the filter capabilities already in the schema.

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 starts with 'Generate an audit report of memory operations,' which is a specific verb+resource combination. It further details what the report shows (remembered, forgotten, merged, by agents, over time period), distinguishing it from sibling tools like memory_recall (retrieve specific memories) or memory_forget (perform forgetting).

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?

The description implies usage when an audit overview is needed, but it does not explicitly state when to avoid using this tool or mention alternative tools for more granular queries. Given the context of many sibling tools, explicit guidance would help, but the current text at least suggests its purpose.

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