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

With readOnlyHint=false and idempotentHint=true already in annotations, the description adds valuable behavioral context: it 'creates durable diagnostic progress' and returns one adaptive question at a time. These are non-obvious side effects and interaction semantics that go beyond the annotations, with no contradiction.

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 short sentences, each earning its place: the first states the action, the second handles the unitId conditional, and the third covers return behavior and side effect. There is no filler or repetition of details already present in the schema.

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?

For a stateful creation tool with an output schema and an idempotency annotation, the description covers the core flow, state creation, and unit scoping. It does not spell out how to submit answers or what subjectSlug values look like, but these are reasonably inferable from context and 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?

The description explains the key unitId behavior—whole-course vs unit-scoped—which the schema leaves undocumented. However, it adds nothing about the required subjectSlug and relies on schema descriptions for intent, requestId, and courseVariant. With 60% schema coverage, this is partial but non-trivial compensation.

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 a specific verb and resource, 'Starts Fiveable's canonical adaptive diagnostic', and the return/side-effect clause distinguishes it from siblings like get_diagnostic_results and submit_diagnostic_answer. The unitId scoping sentence adds precision about the resource scope, making the tool's 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?

It gives clear conditional guidance: omit unitId for full-course coverage or provide an exact unitId to scope to a unit. It also implies the start of an interactive flow by noting it returns one question at a time. It does not explicitly name sibling alternatives, but the context is clear enough.

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