get_audit_log

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

No annotations are provided, so the description carries full burden. It discloses key behaviors: the leading indicator line format, that each write op is one entry separated by blank lines, that reads are not logged, and the backward-paging anchor. The 'what happened lately' rationale adds useful context about intended use. Minor gap: nothing about permission requirements or retention limits.

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 with a leading summary, a behavioral paragraph, and a parameter list. It front-loads the core purpose. Slightly wordy in places (the date format parenthetical and blank-line explanation are essential), but every sentence earns its place. The Args section format is efficient and scannable.

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?

Despite having an output schema (which removes the need to document return format), the description still explains the indicator-line format and entry separation, which adds value. All 3 parameters are documented, the backward-paging nuance is handled, and the read-only caveat ('Reads are not logged') is clearly stated. Complete for a read tool with zero annotations.

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 coverage is 0% (no descriptions in the schema), so the description must compensate fully. It does: each parameter (log_date with YYYY-MM-DD format and default, limit with page-size and 0=count-only semantics, offset with backward-skip meaning) is fully documented with formats and defaults. The backward-offset explanation adds meaning the bare schema cannot convey.

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 specific verb+resource ('Read audit log entries for a date') and clearly distinguishes it from the row-list tools by explaining the unique backward-paging behavior ('offset pages backward into history'). This separates it from sibling list tools like list_customers and list_transactions.

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 explicitly explains when to use it ('what happened lately is the usual question'), contrasts with 'the row-list tools,' and documents the backward-paging semantics and limit=0 count-only behavior. It provides clear context on how the window differs from sibling tools.

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