get_audit

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

Annotations declare readOnlyHint: true, and the description aligns by saying 'Read the action log.' It adds behavioral context beyond annotations: the log is paginated, returns one record per call, and carries specific fields. It also discloses the non-forensic, non-evidence nature, which is critical for appropriate use. This significantly enriches the safety profile.

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 well-structured: it leads with the core action, enumerates the record contents, then adds operational context and limitations. It is a bit long but every sentence adds meaningful information, and the structure is logical. It does not waste words.

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?

With four parameters and no output schema, the description needs to explain how to paginate (limit, start_index) and how to filter (tool, session). It does not. It describes what the log contains but not how to control retrieval. An agent would not know how to request a specific page or filter by tool without inspecting the schema, which itself has no descriptions. The description is incomplete for effective invocation.

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. It does not explain any of the four parameters (tool, limit, session, start_index). It only mentions 'paginated' generically, which hints at limit/start_index but does not explain their meaning or usage. The 'tool' and 'session' filters are entirely unexplained. The description adds essentially no parameter-level meaning.

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 verb and resource: 'Read the action log.' It explicitly lists what each record contains (timestamp, lane, page, URL, resolved target, etc.), which distinguishes it from all sibling tools. None of the siblings (wait_for, get_page_view, find_elements, etc.) read the action log, so the purpose is unambiguous.

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 provides context on when to use it: 'This is an operational record for the user, so you can always know exactly what was done even where a web action cannot be undone.' It also warns of limitations: 'It is not forensic and not evidence.' It doesn't name specific alternative tools, but no sibling appears to offer similar functionality, so the guidance is adequate.

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