record_audit_finding

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

With no annotations, the description carries the full behavioral burden. It hints at a safety boundary ('without expanding mutation authority'), which is a useful behavioral trait, but says nothing about persistence semantics, idempotency, deduplication, or what 'EXPAND' actually triggers.

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 compact clauses with the core action front-loaded and no padding. The second clause is dense but not wasteful in length, even if its meaning is unclear.

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 needn't be described, but with 12 undocumented parameters, no annotations, and an unexplained 'EXPAND' behavior, the definition leaves too much unspecified for an agent to invoke confidently.

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?

There are 12 parameters with 0% schema description coverage, so the description must compensate and largely does not. Only 'EXPAND' vaguely gestures at a finding_class value; required params like audit_id, actor_id, summary, and finding_class are left entirely unexplained.

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 (persist) and resource (audit finding) with a scope qualifier, which distinguishes it from siblings like start_scoped_audit and close_scoped_audit. However, the second clause introducing 'EXPAND' is opaque and doesn't clarify the tool's core purpose.

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 is provided, nor any indication of when to prefer this over start_scoped_audit or submit_verification_observation. The 'EXPAND' clause reads as cryptic jargon rather than actionable usage direction.

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