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

Annotations declare a read-only, non-destructive operation, and the description adds substantial behavior beyond that: version 0 with no blocks means nothing written, nonexistent versions are not-found errors, older revisions include savedAt, and writing is additive rather than history-erasing. This is rich context an agent cannot get from annotations.

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 with the core purpose, then scoping, return shape, and workflow in a dense multi-sentence block. Every sentence carries information, though the rollback sentence and sibling routing make it longer than strictly minimal.

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?

With no output schema, the description compensates by naming the return shape ({courseId, version, blocks} plus savedAt) and edge-case semantics. Nothing needed to call or interpret the result 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 baseline is 3, but the description adds real meaning: what `version` selects (a saved revision from course_version_list), its valid range, and the effect of omitting it. Slightly exceeds the schema's own wording.

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 and the exact representation returned (EditorJS blocks), plus the H2/H3 structural convention. It also distinguishes itself from siblings course_get and fetch by naming what those return instead.

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 routes: use course_version_list to find revisions, course_get for settings, fetch for catalog summary, and read the current version before course_content_set to preserve block ids. It also covers the rollback workflow. When/when-not guidance is fully present.

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