select_courses

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

Goes meaningfully beyond the annotations: it discloses that the operation is a replacement, that an empty array clears without deleting files, that it is a local-only change, and that user approval is required. The annotations already cover idempotency and destructiveHint=false; the only unexplained point is openWorldHint=true, which sits in mild tension with 'Local change only' but reasonably reads as 'no remote mutation' rather than a true conflict.

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, each carrying a distinct fact (precondition, effect, edge case, scope), with the primary action front-loaded. No filler or redundancy.

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 single-parameter, no-output-schema tool with annotations present, the description covers precondition, mutation semantics, empty-input behavior, and scope. It leaves unaddressed what happens with invalid or unmatched IDs and whether the new selection is returned, which would be the only remaining gaps.

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%, yet the description explains what courseIds contains ('observed My Modules IDs') and what an empty array means, which is the key semantic the schema cannot convey. It stops short of noting constraints like the 200-item cap or positive-integer requirement, but those are already 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 target state: 'replace the local course selection with observed My Modules IDs'. The phrases 'Local change only' and 'without deleting files' distinguish it behaviorally from write/transfer siblings like sync_courses and download_resource, so an agent can tell what this mutates without opening the schema.

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 precondition ('After user approval') and an explicit edge-case usage ('Empty courseIds clears selection'). It does not, however, name an alternative tool or state when to prefer this over sync_courses, so the routing guidance is incomplete rather than absent.

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