s21_audit_rubric

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

No annotations are provided, so the description carries the full burden. It communicates that the tool evaluates a draft against a rubric and outputs per-criterion projected scores, which implies a non-mutating analysis. However, it does not disclose whether anything is persisted, whether grades are submitted, what score scale is used, or what the exact output contract looks like.

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?

A single, well-structured sentence delivers the core action and result without any filler. It is front-loaded with the verb and includes the key distinguishing detail ('por criterio'), making it easy for an agent to parse quickly.

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?

The description is adequate for basic selection and invocation, especially with fully documented required parameters. Yet, with no output schema and no annotations, it leaves out useful context such as the expected return format, score range, and whether this operation has any side effects on Canvas.

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%, and the parameter descriptions are already clear. The tool description adds little beyond the schema, but it does reinforce that draft_text is the student draft and assignment_id is the Canvas assignment to evaluate. This meets the baseline for schema-covered parameters.

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 clearly states a specific action ('Comprara el borrador... contra la rúbrica') and a specific result ('evalúa el puntaje proyectado por criterio'). It identifies the tool's resource (Canvas rubric) and differentiates it from the sibling list, none of which offer rubric auditing or draft scoring.

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 intended use is implied by the action: use this tool when you have a student's draft and need a projected rubric score. However, it does not explicitly say when to use it versus alternatives or provide exclusion criteria, though no sibling appears to compete directly with this functionality.

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