wafle_agents_create

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

No annotations are provided, so the description must carry behavioral details. It discloses hard caps on max_cost_per_run_cents (5000 = USD 50) and max_turns (50), and lists the five pre-armed template names. It does not mention potential errors, idempotency, or whether the agent is immediately active, but the key constraints and operational options are disclosed.

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 compact and organized into two numbered paths, making the alternative workflows easy to scan. It passes along critical constraints in a single closing sentence without redundancy. Every sentence adds an operational fact.

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?

Given the tool's complexity (13 parameters, nested guardrails/trigger_config, no output schema), the description covers the two creation modes, prerequisite discovery, and numeric caps. It omits explanation for some optional parameters (model, temperature, tools_disallowed) but the schema contains enough property definitions for those. Overall, the description supplies the essential context beyond the schema.

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 only 23%, so the description compensates by enumerating the from-scratch parameters (name, system_prompt, tools_allowed, guardrails, trigger_type, trigger_config) and by listing the valid template values. It also maps the cap names to their limits, giving context beyond raw schema definitions. Some parameters like tools_disallowed and model are not explained in the description, but the main paths are covered.

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 opens with 'Create a new custom agent,' a specific verb and resource, and clearly distinguishes from sibling tools like wafle_agents_update or wafle_agents_run by detailing two creation paths. It also names the exact template options and outlines the from-scratch parameters, making its scope unmistakable.

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 explicitly tells the agent to use wafle_agents_tool_catalog first to discover available tools, giving a prerequisite for from-scratch creation. It also differentiates the two creation paths and notes that slug/name can be overridden when cloning. It does not explicitly name alternative tools like wafle_agents_update for editing, but the 'create' orientation is clear enough.

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