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

Annotations already establish read-only/idempotent/non-destructive behavior. The description adds useful behavioral detail beyond annotations by specifying output ordering ('curriculum order'), included URLs, and free/subscription flags, making what the caller receives predictable.

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?

Two dense sentences with no filler. Return contents are front-loaded, and the usage scenario follows immediately, earning every word.

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 read-only, idempotent one-parameter tool with no output schema, the description fully covers what the caller gets (full structure, chapters, lessons, URLs, flags) and how to use it, leaving no critical gap.

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 100% and the single required parameter course_id is already documented as 'Course (grade) id, from list_subjects.' The description does not need to add parameter-level detail; the schema carries the burden.

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 uses a specific verb ('Returns') and resource ('the full structure of one grade (course)') and enumerates exactly what is included: subject, chapters in curriculum order, lessons, canonical URLs, and flags. It also distinguishes itself from get_lesson by positioning the output as a means to pick a lesson id.

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 explicitly states when to use the tool: 'Use it to see what a grade covers or to pick the lesson id for get_lesson.' This gives clear context, though it does not state explicit when-not-to-use scenarios relative to other siblings like search_lessons.

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