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

The description states 'Idempotent (re-ratifying updates in place)', which directly contradicts the annotation idempotentHint=false. Even though the sensitive-tier approval behavior is well disclosed, the direct contradiction with a structured annotation triggers the contradiction rule.

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 front-loaded with the core purpose, and each paragraph adds distinct value: persistence semantics, routing, and sensitive-tier approval behavior. Some redundancy exists between the first sentence and the routing line, but the structure is still efficient for a high-stakes tool.

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?

The description covers when to call, what to pass conceptually, idempotency behavior, sensitive-tier approval requirements, and the relationship to derive_capability. There is no output schema, but the operational context is otherwise strong; the main gap is the conflicting idempotency claim.

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%, so the schema already documents features, companyId, and scan_hash adequately. The description adds useful conceptual context about operator ratification and source='derived', but does not provide additional parameter-level syntax or examples, matching the baseline for high schema coverage.

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 states a specific action ('Persist... derived features'), the resource ('product capability index'), and the source ('source=derived'), while explicitly tying it to derive_capability. This clearly distinguishes it from siblings like derive_capability, create_feature, and update_feature.

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 gives clear routing guidance: 'Call ONLY with features the operator has ratified' and explicitly names derive_capability as the prerequisite source. It also notes that can't-do limits are authored separately, which serves as a when-not signal. It does not name a specific alternative tool for unratified features, but the context is unambiguous.

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