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

Beyond the annotations, it discloses who can invoke it (admins), the visibility consequence of each state (drafts visible to admins only, published shows to members immediately), and where related settings are configured externally. It does not clarify reversibility or what is returned, but the annotations already cover the mutation/safety profile.

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?

Front-loaded and reasonably short, but the draft/published behavior is stated twice ('as a draft or published' then 'as a draft unless published is true'), and the clause 'as Classroom, New course does' is awkward filler referencing UI behavior. It could lose a sentence without losing information.

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 5-param mutation tool with full schema coverage and annotations present, the description covers authorization, state semantics, follow-up tooling, and external boundaries. No output schema exists, but the return value is not something an agent strictly needs here; the remaining gap is minor.

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%, so the baseline is 3, but the description adds the access model behind min_level ('Open to all members, or only from min_level up') and clarifies that published=true publishes immediately versus a default draft. It also bounds scope by noting that paid and time-unlocked configuration is done elsewhere, which is genuinely useful context not in the schema.

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 and resource ('Add a course to the group's Classroom') with a clear scope ('as a draft or published'), and explicitly points to the sibling create_lesson for the next step. It does not distinguish itself from set_course_published, which is the nearest overlapping sibling, so it falls short of a 5.

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 a real precondition ('Admins only'), a sequencing instruction ('Add lessons with create_lesson'), and a decision rule for the main branch ('A draft is seen by admins only, so it runs without asking first'). It also notes that paid and time-unlocked behavior lives in Skool. No explicit comparison against set_course_published is offered.

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