Compute Needed Score

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

"Pure math with no writes" reinforces the existing readOnlyHint/destructiveHint=false annotations but adds little beyond them. It does not disclose key behavioral traits an agent would want: whether the calculation reads live Canvas state or a what-if override set, how ungraded/ungraded-group items are treated, or whether a result of null/impossible is possible when the target is unreachable.

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 short sentences with the core purpose front-loaded, the safety/behavior note second, and the sibling routing last. Nothing repeats the schema or wastes tokens.

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 two-parameter, non-mutating math tool with full schema coverage and annotations, the description covers purpose, safety, and sibling routing. The one gap is return shape with no output schema: it doesn't say whether the result is a single required percentage, a per-group breakdown, or an unreachable-target signal.

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%: course_id includes a format example and a pointer to list_courses, and target_percent has an example. The description adds only conceptual context (group weights affect the math) and no syntax or edge-case semantics beyond the schema, so the baseline 3 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?

The description names a specific verb and resource (calculate the average needed on remaining ungraded work to hit a target final percentage) and adds the qualifying detail that group weights are accounted for. It is immediately distinguishable from what_if_grade, so an agent can select it 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?

It states the use case (finding the required average on remaining work) and explicitly names the alternative, what_if_grade, with the condition that selects it: testing one specific score against Canvas itself. That is a direct when-to-use-this-vs-that routing statement.

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