audit_usage

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. It discloses that search result contents are not logged and that results are newest first, which is useful. However, it doesn't state that the operation is read-only, doesn't mention pagination or limits, and doesn't clarify what happens when filters are empty. Some transparency is present but not comprehensive.

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?

The description is two short sentences with no redundancy. The core purpose is front-loaded, and the caveat about search contents is a useful addition. It is concise and to the point, though it could be slightly more informative without losing conciseness.

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?

Given that an output schema exists, return values are covered. However, the description does not explain the four parameters (all optional with defaults), nor does it provide usage guidance or prerequisites. It also doesn't mention any limitations beyond the content logging caveat. For a tool with no annotations and four parameters, this is incomplete.

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 0%, so the description must compensate for the parameters. It does not mention 'llm', 'tool', 'limit', or 'project' at all. The phrase 'who read what and when' hints at filtering by user/tool, but it doesn't map to specific parameters or explain their effects (e.g., limit is a count, tool filters by tool name). The description adds no value for parameter comprehension.

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 states a clear purpose: reporting who read what and when, with newest-first ordering. It implicitly distinguishes itself from siblings like read_memory or search_memory by focusing on an audit log rather than content retrieval. However, it doesn't explicitly say 'audit log' or mention that it returns a list, though the name and phrase 'who read what and when' make the intent clear.

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 is given on when to use this tool versus alternatives like search_memory or recent. It doesn't state whether to use it for access history, compliance checks, or filtering by user/tool/project. The description only describes what the tool does, not the conditions that select it.

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