memory_audit_turn

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

With no annotations, the description carries full responsibility. It discloses side effects ('emits turn_audited always, plus search_miss when miss'), scoping behavior ('auto-scopes to the caller's repo'), the miss detection logic, and return values (MissReport with verdict). This is highly transparent.

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?

The description is dense but every sentence earns its place. It opens with the most critical warning ('Not for in-conversation use'), then covers mechanics, scoping, return, and side effects in three sentences with no filler.

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?

Despite complexity (telemetry, hooks, side effects, output schema), the description covers all necessary aspects: invocation constraints, probe behavior, scoping, miss criteria, events, and return type. It even summarizes verdict values, making it complete even without reading the output schema.

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 0%, so the description must explain parameters. It does so effectively: 'for `user_message` (`assistant_response` optional)' and 'within `lookback_seconds` (default 60)' explains the role and default of each parameter, adding meaning beyond the raw 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?

The description clearly states the tool's purpose with specific verbs: 'Runs the search probe', 'checks whether a retrieval event fired', 'Returns a MissReport'. It distinguishes from siblings by explicitly noting it is 'not for in-conversation use' and is dispatched by the Stop hook, not meant for direct model invocation.

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 states when NOT to use it ('The model should never call this directly') and when it is used (dispatched by end-of-turn Stop hook). However, it does not explicitly name an alternative tool for direct memory search, though the reference to `memory_search` as the probe implies it.

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