get_audit_log

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

With no annotations, the description carries the full burden. It discloses one genuinely useful behavioral trait - email bodies are never stored, so the agent should not expect message content - and 'Read' implies a non-mutating operation. It omits auth/permission requirements, retention window, and ordering of entries.

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 tight sentences with no filler; the purpose is front-loaded and the privacy caveat is a deliberate second line. Every sentence earns its place.

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 no output schema and no annotations, the description should carry more about the shape of returned entries (fields, ordering, timestamp format). It gives the high-level subject and a key exclusion but leaves the return contract underspecified.

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% with a single optional 'limit' parameter whose bounds and meaning are fully documented in the schema. The description adds nothing beyond the schema ('recent' merely echoes the default ordering), so the baseline 3 applies.

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?

States a specific verb (Read), resource (audit metadata), and scope (recent, local, write actions). This clearly separates it from the email-centric siblings like list_messages and get_message. It does not, however, clarify what 'audit metadata' actually contains beyond the exclusion note.

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 implies the usage context (reviewing a trail of write actions) but never states when to reach for this tool versus any alternative, and gives no prerequisites. Adequate but leaves routing to inference.

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