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

With no annotations supplied, the description carries the full behavioral burden. It usefully discloses that writing a money value does not require see_prices, but says nothing about overwrite semantics, whether the field must be defined first, what happens on type mismatch with the field definition, or whether currency is required alongside money values.

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 short sentences with the core operation front-loaded and the permission note second. The internal reference code 'D-20261106-CF-4' is noise an agent cannot use, which slightly weakens an otherwise efficient statement.

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?

This is a write tool with six parameters, five required, no annotations and no output schema, yet the description explains neither the key/target relationship, the currency requirement for money, nor the failure modes. For a mutation endpoint with almost no schema documentation, far more disclosure is needed.

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 only 17% — just the 'value' property is documented — so the description must compensate for key, target, object_id, shop_id, and currency. It adds no meaning for any of these, not even clarifying that 'key' is the field key from fields_define or when 'currency' is needed for money values.

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 (set) and resource (one custom field value) plus the exact set of target entity types, which separates it from fields_define/fields_get/fields_list by implication. It stops short of naming those siblings explicitly, but the scope is unambiguous.

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 guidance on when to use this versus fields_define (creating the field definition) or fields_get (reading values), and no prerequisite such as 'the key must already exist as a defined field.' The only usage-like remark concerns permissions, not tool selection.

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