audit_entries

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

With no annotations, the description carries the full burden and delivers: it declares READ-ONLY safety, newest-first ordering, response semantics (matched/total/truncated), and a nuanced null-principal behavior that prevents misinterpretation as a blame claim. This is far beyond a typical minimal description.

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?

Front-loaded with the safety marker and core purpose, then progressively covers use cases, response metadata, edge-case behavior, and sibling contrast. Every sentence earns its place; nothing is redundant or filler despite the length.

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?

Lacking both annotations and an output schema, the description compensates by explaining the return shape (matched/total/truncated), null-principal behavior, and ordering — plus differentiating the closest sibling (audit_verify). For a 5-param read-only query tool, this is complete.

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 covers all 5 parameters (100%), so baseline is 3. The description adds value by explaining how the filter params relate to the `matched` count and how `limit` triggers `truncated`, enriching the semantic meaning of both filter and pagination parameters beyond the schema text.

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?

Opens with 'READ-ONLY: WHO changed WHAT and WHEN' — a specific verb (read) plus resource (PROVE ledger) and scope (guest config changes and all audited actions). It clearly distinguishes itself from the sibling audit_verify by stating it READS the chain while audit_verify PROVES integrity.

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?

Explicitly frames usage: 'This is how you answer "who changed this guest" or "what has this caller done"'. It also gives a when-not signal by contrasting with audit_verify ('This READS the chain; audit_verify PROVES it is intact'), steering the agent to the right sibling for integrity checks.

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