lattice_get_audit_log

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

With no annotations, the description must convey behavior. It states 'recent' and filtering capabilities but omits details like time range boundaries, pagination behavior (offset), or read-only nature. For a read-heavy audit tool, these are moderate gaps.

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?

Two sentences, no wasted words. The first sentence states the core function, the second provides a concrete use case. Perfectly front-loaded and compact.

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 simple retrieval tool with well-documented parameters, the description covers the key aspects. Missing details like sorting order and result format, but output schema is absent and schema already defines parameters. Minor gap for a complete contextual picture.

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 100%, so baseline 3 is appropriate. The description reinforces the purpose of the parameters (e.g., 'filter by...') but does not add new semantics beyond the schema's property descriptions.

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 states the tool retrieves recent audit log entries with specificity: 'who did what, when'. It distinguishes itself from sibling tools like metrics or container management by focusing on audit logs, and mentions key filtering dimensions (user, action, resource type).

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 suggests using filters to answer specific questions like 'who deleted X' without scanning, which implies efficient forensic usage. It does not enumerate when not to use or provide alternative tools, but the context of sibling tools makes the intended use clear.

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