Final Grade Scenarios

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

Annotations already declare readOnly, idempotent, non-destructive, so safety is covered. The description adds genuine model context beyond that: it uses the course's assignment-group weights and Canvas letter cutoffs, with a fallback caveat ('when Canvas shares them'). It omits what happens to ungraded items or the response shape, keeping it from 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?

One dense sentence front-loads the purpose and outputs, followed by a short data-source note and 'Read-only.' There is little wasted wording, and the most important information leads.

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 no output schema, the description does the work of naming the returned values (projected grades at several averages, needed averages per letter) and the weighting source. It is nearly complete for a two-param read tool, missing only edge-case behavior on ungraded assignments.

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 100%, so course_id and targets are already documented. The description adds useful context by documenting the implicit default scenarios (100/90/80/70/60%) that the schema does not surface, but it never mentions the custom 'targets' override that the schema defines.

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 ('What-if planning for a whole course') plus the exact outputs: projected final grades at 100/90/80/70/60% and needed averages per letter. The 'whole course' scoping implicitly separates it from the single-item what_if_grade and compute_needed_score siblings.

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?

The opening 'What-if planning for a whole course' implies when to reach for it, but there is no explicit when-to-use vs when-not, and no mention of alternatives like what_if_grade, compute_needed_score, or get_course_grade_breakdown. The agent must infer the boundary from the 'whole course' phrasing alone.

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