Schedule Study Plan

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

Adds substantial context beyond the annotations: privacy ('Only you see them'), a hard batch ceiling of 60 blocks per call, and an explicit two-step preview/execute protocol flagged as irreversible. The annotations only declare non-read-only, non-idempotent, non-destructive; the irreversible-create nuance and the confirmation flow are non-obvious and only appear in the description.

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 compact sentences front-load the purpose, then follow with the privacy note, the size limit, and the critical confirm warning in brackets. Nothing is redundant and the most dangerous fact (irreversibility) is visually isolated.

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 write tool with no output schema, it covers purpose, limits, privacy, and the confirmation protocol, which is close to everything an agent needs. The one gap is what a dry-run preview returns or what the executed call returns (IDs, counts), which would help the agent verify success.

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 real meaning: it identifies study_plan as the source of the blocks payload and imposes a 60-item cap that the schema does not encode (schema only sets minItems: 1). It reinforces rather than repeats the confirm semantics.

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 concrete verb and resource ('Put study blocks ... on your personal Canvas calendar'), names the source tool (study_plan), and distinguishes the two destinations (calendar events vs planner notes). An agent can tell this apart from create_personal_event or create_planner_note without reading 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?

Explicitly tells the agent to call first without confirm=true for a preview, then re-call with confirm=true, and notes that host apps may surface their own confirmation instead. It also says the blocks usually come from study_plan. It stops short of naming alternatives (create_personal_event, create_planner_note) or when a single ad-hoc event should be preferred over a batch.

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