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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds domain behavior beyond that — that values are computed from a formula or an AI instruction, that staleness is reported, and that a monthly AI allowance is surfaced — which is genuinely useful context. It stops short of describing pagination, ordering, or the fact that results are scoped to a single merchant, despite the title implying a plain list.

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?

Under-specification, not conciseness, is the issue here — the description is a single dense run-on covering the smart-field concept and how to reference fields inside product cells, with no filler sentences. It is front-loaded with the resource definition and the core detail (computed from a rule, plus staleness and allowance counts) arrives first.

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 an output schema and full annotation coverage, this description still leaves the central lookup—when an agent should call list_smart_fields versus create_smart_field or generate_smart_field—entirely unstated. The single sentence on catalogField and product cells is helpful surrounding context, but it does not fill that behavioral gap for a routine listing tool.

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?

The tool takes zero parameters, so the baseline is 4 and there is no parameter meaning to compensate for. The description's mention of `output` (text, rich_text or boolean) and `catalogField` describes response fields, not inputs, which is orthogonal to the input schema rather than additive to it.

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 opens with a noun phrase, 'The merchant's smart fields', and spends most of its words defining what a smart field is rather than stating a listing action. The enumerated contents (counts of products with a value, out-of-date counts, AI allowance, output kind) imply enumeration, but there is no explicit verb and no mention of the sibling tools create_smart_field or generate_smart_field that a caller would otherwise consider.

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?

There is no statement of when to call this tool versus create_smart_field, generate_smart_field, or get_catalog. The one directive present, 'Use a text field in a catalog by its `catalogField` (`fields.<key>`) in a product cell's fields', concerns how to consume field values downstream rather than how to use this tool, so it does not function as usage guidance.

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