cortex_audit_contradictions

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

No annotations are supplied, so the description carries the full burden. It does disclose meaningful behavior beyond the schema: the detection categories and the fact that resolutions may be recommended or applied via supersession. However, it never states the default is a safe read-only scan, the cost/latency of a full-graph audit, or that supersession preserves history in a bi-temporal store rather than deleting facts.

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 front-loaded sentence with the action first and the parenthetical category list earning its space by defining the detection scope. It is dense but free of filler; the trailing 'recommend or apply supersession resolutions' is the only slightly compressed clause.

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 two optional parameters, no output schema, and no annotations, the description is adequate but leaves gaps: it does not describe what an audit returns (a report of conflicts? proposed resolutions?) or clarify that omitting auto_resolve leaves data untouched. For a tool that can mutate the graph, the safe-by-default behavior should be explicit.

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 100% and both parameters (as_of, auto_resolve with default false) are already well documented in the schema. The description adds only the framing that 'active facts' can be audited at a historical point and that resolutions are supersessions; it adds no syntax, format, or edge-case detail beyond the 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 pairs a specific verb ('scan/detect') with a specific resource ('active facts in the bi-temporal graph') and then enumerates the exact contradiction classes it finds (negation polarity inversions, antonym objects, predicate alias collisions, unsuperseded multi-value drift). That enumeration distinguishes it from a generic integrity checker such as memory_verify_integrity without needing to name it.

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?

Usage is only implied: an agent can infer it should call this when it suspects conflicting facts, and the 'recommend or apply' phrasing hints at a read-then-mutate workflow. There is no explicit statement of when to prefer this over memory_verify_integrity or memory_query_entity, and no stated preconditions.

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