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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, so the safety profile is partially covered. However, the description does not resolve the key ambiguity a destructive update raises: whether supplied fields replace all existing preferences or merge with them. It also omits that request_instant_scoring triggers an AI-scored lead return, which is a meaningful side effect.

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?

Three tight sentences, front-loaded with the primary natural-language workflow and followed by the fallback direct-field option. No filler, though the closing sentence largely repeats parameter names already visible in the schema.

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?

For a six-parameter, destructive, no-output-schema mutation tool, the description covers the input mechanism adequately but leaves gaps on the two things an agent most needs: merge-vs-replace semantics of the update and what request_instant_scoring returns.

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 all six parameters are already documented with examples and accepted value sets (employee ranges, buying signal enums). The description echoes four of them (industries, locations, employee sizes, buying signals) but adds no semantics beyond the schema and omits ideal_customer_profile and request_instant_scoring. Baseline 3 applies.

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?

Clear verb+resource ('update your targeting preferences') with the mechanism (natural-language parsing plus direct field specification) spelled out. It implicitly contrasts with the sibling get_targeting_preferences via 'update' vs 'get', but never names that sibling to make the distinction explicit.

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 conveys two usage modes (natural language vs explicit fields), which is useful context, but it gives no when-to-use/when-not guidance and never points to get_targeting_preferences or get_saved_filters as the way to inspect existing settings first. Usage is implied rather than directed.

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