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

Annotations only declare destructiveHint=false. The description adds meaningful behavioral context by specifying what the tool returns and the expected sequence (start, run intake, then teach). This goes beyond the annotation without contradicting it.

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 two concise sentences, front-loaded with the primary action, and includes no filler. Every sentence adds value: the first states the action and outputs, the second gives the workflow.

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?

An output schema exists, so return-value details are covered. The description provides the essential workflow and return content. However, parameter semantics are thin, and the term 'intake' is introduced without explanation, leaving minor gaps. Still, it is mostly complete for a starting 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?

Schema description coverage is 0%, so the description must compensate for parameter meaning. While 'course' is implicitly the course to start, the description does not clarify the expected format (e.g., course ID, slug) or the role of auth_token. The parameter semantics are largely undeveloped.

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 clearly states 'Start a course' with a specific verb and resource, and further distinguishes the tool by listing its specific outputs (tutor protocol, intake guidance, module map). It uniquely identifies this as the entry-point tool, setting it apart from sibling tools like start_exam or start_interview.

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 explicit workflow guidance: 'Call this first, run the intake, then call teach_section to teach Module 1.' This tells the agent exactly when to use it and even names the next tool to call, making the usage sequence unmistakable.

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