ilias_scan

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description must add context rather than restate safety. It does: it discloses that results are relative to a previously committed baseline, that the call returns a scan_id, and that the baseline is only advanced by a separate commit call. Not disclosed: whether an uncommitted scan leaves any server-side state, or how large a crawl (depth) affects runtime.

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: what it does, what it returns, and the required follow-up. The diff behavior and the commit dependency are front-loaded with no filler or restated field names.

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?

An output schema exists, so return shape need not be described, and the stateful workflow is covered. For a crawl tool with four undocumented parameters, however, the undefined target format and depth semantics are real gaps an agent could get wrong on first invocation.

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 description coverage is 0%, so the description carries the burden, and it only partially does so. 'One course' implies target is a course identifier, and the mention of assignments and forum threads maps loosely to include_assignments/include_forums, but neither the expected target format (ID vs. URL) nor the meaning of depth is explained anywhere.

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?

Specific verb ('crawl') plus resource ('one course') and a precise result definition (new/changed/removed items, assignments and forum threads versus the last committed scan). That diff-based, stateful framing distinguishes it from plain listing siblings such as ilias_list_items and ilias_list_courses, though it never contrasts itself with ilias_check_all, which is the nearest-looking alternative.

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 clear workflow obligation: after findings are recorded, call ilias_commit_scan so the next scan compares against this baseline. That is genuine when-to-use guidance and names the sibling. It does not, however, say when to prefer this over ilias_check_all or when a scan is unnecessary, so exclusions are absent.

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