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

Annotations declare it non-read-only but idempotent and non-destructive; the description adds the crucial behavioural fact that the default is a dry-run preview and that persistence requires explicitly setting preview_only=false plus a name. That default-writes-nothing nuance is exactly the kind of context annotations cannot convey. It stops short of explaining idempotency_key or how segment_id alters behaviour.

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 tight sentences, zero filler, and the primary behavioural fact (preview by default) is front-loaded. Nothing is restated from the title or 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?

The tool takes a recursive filter tree, an optional segment_id, and an idempotency_key, yet the description never says whether segment_id updates an existing segment, how idempotency_key is used, or what the preview returns. With no output schema and 20% parameter coverage, a two-sentence description leaves material gaps for a tool of this complexity.

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?

With only 20% schema description coverage, the description compensates by explaining preview_only's default and the conditional requirement that name is needed to persist — a constraint the schema does not encode (name is not listed as required). However the required, complex 'filters' tree and segment_id/idempotency_key receive no additional meaning beyond the schema text.

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 (define/preview/persist) and resource (filtered contact segment), and the preview-vs-persist split is clear. It does not, however, differentiate itself from near-neighbours like nitro_search_contacts or nitro_manage_audience, which an agent may consider for overlapping contact-filtering work.

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?

It gives a concrete rule for the two modes ('preview_only defaults true; set false and provide name to save'), which is real when-to-use guidance for the persist path. But it never names an alternative tool or says when this tool is preferable to searching or managing audiences, so tool selection is still left to inference.

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