audit_recent

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

With no annotations, the description carries the behavioral disclosure burden, and it does disclose the key behavior: events are returned newest first and come from the same audit log as audit_search. For a simple, one-parameter read-only tool, this is adequate, though it does not mention maximum limits or output details.

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 filler. It front-loads the core behavior and adds only the useful cross-reference to audit_search, making every word earn its place.

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 single-parameter read tool with an output schema, this description conveys what is returned, how many, in what order, and from which log source. It is reasonably complete; the only notable omission is explicit guidance on when to prefer audit_search, but that is more of a usage-guidelines concern.

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 schema has one parameter, 'limit,' with no description, so the description needs to clarify it. 'Last N' directly maps N to the limit parameter and explains that it controls how many events are returned, adding meaning beyond the raw schema. It does not specify bounds or behavior when omitted, but the schema already supplies the default.

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 clearly identifies the resource as audit events, limits them to the last N, and specifies newest-first ordering. It does not use an explicit imperative verb like 'List' or 'Get,' but the intended operation is unmistakable, and the reference to audit_search helps distinguish it from the search sibling.

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 phrase 'Same log as audit_search' implies that audit_recent is the simple recent-events counterpart to a searchable audit API. However, it does not explicitly state when to choose audit_recent over audit_search or mention any exclusions, leaving the usage guidance implied rather than direct.

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