What to study today

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered; the description adds what is actually returned (per-day sessions, topics when exams have topics, due and late reviews) and that dates may be plain text. It doesn't discuss failure modes for ambiguous date phrases, but for a read-only query tool the added behavioral context is solid.

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?

Purpose and scope are front-loaded in the first clause, and the worked example prompt is genuinely useful for a natural-language-heavy input. There is minor redundancy — plain-text date formats appear in the description and again in every date property — but nothing is wasted at the sentence level.

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 8 all-optional parameters and no output schema, the description carries the return-value burden and does so (sessions, topics, due/late reviews) while noting the date default. It leaves days_off, intervals_days, and start_date entirely to the schema, which is acceptable given 100% schema coverage but leaves the plan-horizon behavior unstated.

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 non-obvious semantics: exams/hours should mirror build_study_plan inputs (including hours_per_weekday), and reviews pair a topic with the day it was first studied. That cross-tool consistency guidance is value the schema cannot convey.

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 resource with explicit scope: the study sessions the plan gives for one day, each session's topic, plus spaced repetition reviews that are due or late. It names the sibling build_study_plan as the source of the same exams/hours, so an agent can tell how this differs from the full-plan tool.

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 concrete invocation guidance: pass the same exams and hours as build_study_plan, including hours_per_weekday, plus reviewed topics with their first-study day; omitting date means today. It stops short of explicit exclusions (e.g., 'for the whole schedule use make_study_plan instead'), so the when-not is only implied by the one-day framing.

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