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

Annotations already declare readOnly/idempotent/non-destructive, so the safety bar is covered. The description adds information annotations do not carry: the response contents (type, options, description, and how many records hold a value) and a cost signal ('Free'), which is genuinely useful for planning.

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?

One front-loaded sentence with no filler, and the parenthetical efficiently delivers both return-shape and provenance information. It is dense to the point of being slightly clipped, but nothing is wasted.

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 small, read-only discovery tool with no output schema, the description adequately covers what the tool returns and what the custom-field concept means. The only material omission is the behavior when the optional 'object' filter is not supplied.

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 coverage is 0%, but the single parameter is an enum that self-documents its three legal values, and the description echoes them as contact/company/deal. The real gap is the optional parameter's default: the description never says what is returned when 'object' is omitted (presumably all three types).

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 names the resource precisely ('the fields you can read, filter and sort on') and enumerates the three object scopes, so its function is unmistakable. It also distinguishes the standard set from custom fields defined via the sibling crm_define_field, though it does not explicitly contrast itself with other crm_list_* tools.

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 framing 'fields you can read, filter and sort on' makes the use case clear: schema discovery before filtering/sorting or before writing custom-field values. It names crm_define_field as the creation counterpart, but gives no explicit 'do not use this to create fields' exclusion or a stated precondition like 'call before crm_find_contacts with custom filters'.

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