export_audit

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

Description discloses read-only nature, direct text return (no JSON wrapper), format behaviors (jsonl one per line, json array, csv header+rows), and time filter application. Lacks mention of size limits or error handling, which is acceptable given tool simplicity.

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?

Description is concise (5 sentences), front-loaded with purpose, then usage guidance, then format details. No redundant or filler content. Each sentence adds value.

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 an export tool with no output schema, description fully explains return format, parameter behavior, and usage context. Includes sibling references and typical workflows, making it comprehensive.

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 descriptions, but the description adds meaningful context: explains format nuances (stream-friendly jsonl, spreadsheet-friendly csv) and states 'Time filters are applied to event timestamps before formatting,' which clarifies processing order beyond 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?

Description clearly states it exports audit log as portable text artifact for archiving or SIEM feeding, and distinguishes from sibling tools: `audit_log` for in-conversation tail and `verify_audit_chain` for integrity check before export.

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 lists use cases (compliance exports, after-the-fact investigations, non-MCP consumer hand-off) and when alternatives are better (prefer `audit_log` for tail, `verify_audit_chain` before exporting).

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