codex_audit

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

With readOnlyHint and idempotentHint already covering the safety profile, the description contributes 'bounded page' pagination semantics, a machine-readable return format, and a concrete output claim (research-bridge paths). It adds meaningful context beyond the annotations and does not contradict them.

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?

A single 13-word sentence with the verb front-loaded. 'Bounded page,' 'machine-readable,' and 'research-bridge paths' each add a distinct constraint with no filler or redundancy.

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 zero parameter documentation, the burden falls on the description for return shape and cursor semantics. It hints the output contains research-bridge paths but never explains what those are, nor how after_seq and limit drive paging, so an agent can make a basic call but cannot page correctly or anticipate the response structure.

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 explain the three parameters to compensate. It only vaguely gestures at pagination with 'bounded page'; task_id — the sole required parameter — and the after_seq cursor are never mentioned, leaving their semantics to inference.

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?

Uses a specific verb ('Read') and a specific compound resource ('a bounded page of machine-readable audit events ... research-bridge paths'). The output focus on 'research-bridge paths' sets it apart from generic event readers like codex_events and the writer codex_record_audit_event, though it never names those siblings explicitly.

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?

No when-to-use guidance appears in the description. An agent choosing between codex_audit, codex_events, and codex_status gets no selection criteria, and the relationship to codex_record_audit_event is never clarified.

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