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

Annotations only declare readOnlyHint/openWorldHint, but the description adds substantial behavior: newest-first ordering, first row is the current version, versions accumulate and are never pruned, authorName appears only with members:read, the exact return shape, and that restoring adds a new version rather than overwriting history.

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-loads the purpose before any procedural detail, and each following sentence adds a distinct actionable fact. Nothing redundant.

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?

Although there is no output schema, the description spells out the returned object shape ({courseId, total, count, versions}) and the per-row fields, and it explains the read-only, accumulating nature of the version history. Nothing an agent needs to call it correctly is missing.

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 defaults and caps are already documented. The description nevertheless adds operational meaning beyond the schema: paging back by raising offset in steps of limit, and using limit:1 to read the current version's number and save time.

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, resource, ordering and scope: 'List a course's saved content versions, newest first, as metadata only', then enumerates exactly which fields come back. It clearly distinguishes itself from course_content_get, which returns blocks rather than version indices.

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?

Explicitly names the situation to use it (find an earlier version to inspect or restore) and the situation not to (reading current lessons, which course_content_get returns by default), and routes to the correct sibling for each follow-up action. Also covers pagination and restore procedures.

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