Create an agent

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

Annotations only carry idempotentHint:false (confirming this is a non-idempotent write), so the description must do the rest — and it does, disclosing the scope requirement, plan-level agent cap, provider/language restrictions, and the two_way default for communication. It does not describe what happens on limit breach or what the response contains, but for a creation call the behavioral coverage is solid.

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?

Three tight sentences with the mode distinction front-loaded, then rules, then the one-way configuration, then the scope requirement. No filler and nothing buried.

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, the description need not explain return values, and it covers the scope, defaults, plan limits, and the two-way/one-way conditional structure adequately for a nested-object creation tool. Minor gap: it doesn't say which identifier comes back or whether the agent is usable immediately after creation, which matters for chaining with place_call or update_agent.

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%, so a 3 is the floor, but the description adds cross-parameter conditional semantics the schema does not express: prompt is two-way only and omitted entirely for one-way, announcement is required when communication is one_way, and communication defaults to two_way. That conditional logic is the main value-add for a 5-param nested-object tool.

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 (Create) plus resource (agent) and immediately distinguishes the two variants it can produce: conversational/two-way versus one-way script-only with no listening. An agent can tell this apart from get_agent, update_agent, and create_campaign without opening any schema.

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?

Gives concrete routing guidance for the one-way path (set communication:"one_way" and pass announcement:{script, useCase}) and surfaces prerequisites: the plan's agent limit, provider/language restrictions, and the required "agents" scope. It lacks an explicit when-not-to-use or a named alternative tool, which keeps it from a 5.

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