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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=false, so the safety profile is covered. The description adds the custom_fields:write scope requirement, which is genuinely useful auth context beyond the annotations, but says nothing about duplicate-name handling, failure modes, or side effects on existing records.

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, zero filler, with the core action front-loaded and the scope constraint following it. Every word earns its place.

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 7-parameter mutation tool this is adequate but thin: annotations cover the safety profile and the schema covers the parameters, yet the description omits the select/field_options dependency, uniqueness constraints on field_name, and any indication of what a successful create returns (no output schema exists).

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 100% and all three required fields plus the optional ones are documented in the schema, so the baseline is 3. The description adds no semantics beyond the schema and notably does not flag the conditional requirement that field_options is needed when field_type is 'select'.

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 and resource ('Create a new custom field definition'), which is unambiguous on its own. It does not, however, differentiate from the very similar sibling create_custom_field_value (which creates a value, not the definition) or from the create_* family generally.

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?

No when-to-use guidance, no exclusions, and no routing to alternatives such as create_custom_field_value or update_custom_field_definition. The only conditional information given is the required scope, which is a prerequisite rather than usage guidance.

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