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

With no annotations provided, the description carries the full burden. It discloses a real side effect (costs 1 credit), the DRAFT status, and importantly that the agent does not begin contacting anyone upon creation. This is strong behavioral context; only minor gaps remain, such as return value or failure behavior.

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 dense but not bloated, and it front-loads the core purpose and credit cost before explaining workflow steps. Every sentence adds relevant context, though the company-info sentence is slightly convoluted and could be tightened.

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 richly covers cost, draft behavior, required fields, and next steps, but it undermines itself by saying company info can be passed here when the schema does not allow it. This contradiction could cause an agent to construct an invalid call. The absence of any return-value guidance is also a minor gap since 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 both name and description already have clear parameter descriptions, so the baseline is 3. The description adds useful workflow context about required fields and company info, but it also says company info can be 'passed here' even though the schema has no such parameters and additionalProperties is false, which is misleading.

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 AI sales agent,' naming a specific verb and resource. It is clearly distinct from siblings like create_campaign and set_agent_company, and the 'new' qualifier separates it from update_agent.

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 gives explicit usage context: required fields, DRAFT status, the fact that the agent won't contact anyone until attached to a campaign and launched, and the alternative of calling set_agent_company later for company info. This tells the agent exactly when and how to use the tool.

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