get_audit_log

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

Annotations carry readOnlyHint=true, and the description adds rich behavioral context beyond that: backward-pagination semantics, limit=0 returning count only, the leading indicator format, blank-line separation per write operation, and the fact that reads are not logged. No contradiction with the read-only annotation.

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 longer than average, but each section earns its place: the output-format indicator, the genuinely non-intuitive backward-pagination behavior, and the enumerated args. It is appropriately front-loaded and structured into paragraphs plus an Args block. Slightly verbose but justified by the unusual semantics.

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?

An output schema exists, so return values need no explanation, yet the description still covers the indicator line. The most error-prone behavior (reverse offset ordering) is fully disclosed, and the read-only annotation is reinforced by the 'Reads are not logged' note. Nothing an agent needs to call this correctly is missing.

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 fully compensate. It documents all three parameters with meaning beyond the schema: log_date (YYYY-MM-DD format, defaults to today), limit (page size, 0=count only), and offset (entries to skip back from most recent, 0=newest). This fully compensates for the zero-coverage schema.

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 uses a specific verb-resource pair ('Read audit log entries for a date') and adds concrete detail about what is returned (human-readable text, blank-line separated entries, 'Showing X-Y of Z' indicator). This clearly distinguishes it from the many sibling tools, none of which are audit-log readers.

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 contrasts with 'the row-list tools' by explaining that the window anchors to the most recent entry and that offset pages backward — important guidance for a non-obvious API. It also states that reads are not logged. However, it does not name specific alternative tools or give explicit when-not-to-use conditions, so the guidance is contextual rather than prescriptive.

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