Create Field Rule

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

The description significantly exceeds annotations by detailing non-idempotency ('calling it again creates another record'), uniqueness constraints on the scope tuple, error statuses (401, 403, 404), and the return of the new id with HTTP 201. These behaviors are not fully covered by annotations (idempotentHint=false, readOnlyHint=false) and add critical runtime context.

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 concise and front-loaded with 'Creates a field rule,' followed by targeted details. Every sentence adds information about scoping, uniqueness, defaults, idempotency, or error handling, with no filler. It also includes the API endpoint, which is useful context.

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?

The description covers key aspects: behavior, uniqueness, errors, and return id. However, it does not explicitly state the company scope vs. project scope (though implied by endpoint) and does not describe the full response structure beyond the new id. Given the absence of an output schema, this is a minor gap, but the description is otherwise thorough for a create 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?

With 100% schema coverage, the baseline is 3, but the description adds valuable semantic meaning: it explains the scope tuple (asset type, fieldset, trigger field) and its uniqueness requirement, and notes that company_id defaults to the configured value. This goes beyond the schema's individual parameter descriptions.

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 states 'Creates a field rule' with a specific verb and resource, and further clarifies the scope for FIELD_DEFAULTS. The endpoint and company_id reference distinguish it from project-scope siblings like create_field_rule_project_scope, making the purpose 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?

The description provides clear context on when to use the tool (e.g., for FIELD_DEFAULTS with scoping, unique tuple constraint, company_id default). It does not explicitly mention alternatives like project-scope field rules, but the company-level endpoint and company_id behavior imply the scope, so the guidance is clear though not exhaustive.

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