get_pending_subjects

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

Annotations already cover read-only/idempotent/non-destructive, so the bar is lower; the description still adds auth context ('Requires login'), the rule that disagreements are surfaced in discrepancies rather than silently resolved, and the elective N-of-M completion model. 'Read-only' merely restates the annotation, but the discrepancy and derivation semantics are genuine added value.

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?

Front-loaded with the core meaning ('Subjects still to complete:') before the dense computation rules. Sentences carry distinct semantic load, though the em-dash-heavy style packs several rules into long clauses.

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?

No output schema exists, so the description must characterize the return payload, and it does: names and credits, category totals showing how far short, VTOP's own row marking, and a discrepancies section. An agent knows both what triggers the tool and what comes back.

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?

Zero parameters, so there is nothing to document and the schema is trivially sufficient. Baseline of 4 applies.

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 resource and scope: the curriculum basket courses still outstanding after grade-history passes are subtracted. An agent can tell it computes pending status rather than a raw listing like get_curriculum_baskets or get_grade_history, though it never names those siblings explicitly.

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?

Usage is implied by the name and the phrase 'Subjects still to complete' — reach for it when you need outstanding requirements. There is no explicit when/when-not statement and no named alternative to route between against get_curriculum_progress or get_course_basket.

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