Study Plan

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the 'Read-only' line is largely redundant. What the description adds beyond that is real substance: the tool estimates per-item hours, distributes them before each deadline, respects the user's study hours, and works around the Canvas calendar. It stops short of describing the returned structure (per-day blocks, warnings when time is insufficient), which keeps it off a 5.

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?

Two tight sentences with no filler; the core action and its algorithm come first, and the read-only/next-step statement is placed at the end where it functions as the handoff. Every clause carries information.

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 seven-parameter, annotation-rich, output-less planning tool, the description covers the algorithm, the constraints it honors, and the mutation boundary. The one gap is the shape of the proposal itself (what a block looks like, what happens when a deadline cannot be satisfied), which an agent might want to know before deciding how to interpret the result.

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. The description earns the extra point by explaining how parameters combine conceptually: 'next N days' maps to the planning horizon and 'inside your study hours' frames day_start/day_end as a per-day window that blocks must fit within, which is a relationship the flat schema does not make obvious.

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 deliverable ('Propose study blocks for everything due in the next N days') and then explains the underlying computation: estimate hours per item, then spread them across the days before each deadline within study hours. It also explicitly names the sibling it is not (schedule_study_plan), so an agent can separate the preview tool from the commit tool without opening either 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 both when-to-use and the alternative: this tool only proposes, and 'use schedule_study_plan to put the blocks on your calendar' is the explicit follow-up path. The read-only constraint plus the named commit tool is exactly the routing information an agent needs for a plan/apply pair.

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