Create custom value

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

Annotations already indicate this is a mutation (readOnlyHint false) and non-idempotent, so the description need not repeat that. However, it adds no information about behavior beyond creation — e.g., whether duplicate names are rejected, whether the operation is scoped to a location by default, or what happens on failure. The openWorldHint true isn't elaborated. The description carries no extra behavioral context beyond the schema and annotations.

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?

The description is a single, concise sentence with the action and key parameters front-loaded. It avoids extraneous wording and is easy to parse. However, it might be slightly too terse, missing nuance about the locationId parameter and the merge field concept.

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 no output schema and no mention of return values, success indicators, or error conditions, an agent cannot fully anticipate the call's outcome. The description misses the locationId default (though the schema covers it) and does not clarify whether the operation is scoped to a specific location or the default. Given it's a mutation with openWorldHint true, more context about side effects or uniqueness would be valuable.

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 33% (only locationId has a schema description). The description names 'name' and 'value' as required but does not explain what constitutes a valid name or value (e.g., allowed characters, length limits, uniqueness constraints). Since coverage is low, the description should compensate, but it offers no additional semantics beyond restating the parameter names.

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 clearly states the verb 'create' and the resource 'custom value (merge field)', which is specific enough to distinguish from the many related CRUD tools like update/delete/list. The parenthetical clarifies what a custom value is, adding a useful hint. However, it doesn't explicitly contrast with the separate 'custom field' tool (ghl_create_custom_field), so a slight ambiguity remains.

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 implies usage (create a new custom value when needed), but it does not explicitly state when to use this over alternatives (e.g., when to use update vs create, or whether this is for a specific location). Given the sibling list includes update/delete/list, an explicit note about 'use this to create a new value, use update to modify an existing one' would improve it. No such guidance is present.

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