grade_with_rubricGrade one or more submissions (up to 30, in parallel) against a rubric you supply: each criterion scored on a 3- to 6-point scale, summed per submission. Each submission is graded in its own call, so its score never depends on the others.
| Name | Required | Description | Default |
|---|---|---|---|
| points | No | ||
| criteria | Yes | Rubric rows, e.g. { "name": "Evidence", "description": "Supports the claim with specific evidence" }. | |
| assignment | No | ||
| submissions | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only cover readOnlyHint/openWorldHint, but the description adds real behavioral context: submissions are graded in parallel and each is scored in its own call so scores are independent of the others — an important determinism guarantee an agent would not otherwise know. It does not contradict the read-only annotation.
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?
Two dense sentences with zero filler; the batch/parallel scope and the rubric mechanism are front-loaded. Every clause carries information.
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 should explain the return shape (per-criterion scores and per-submission sums). 'Summed per submission' hints at the result but is thin, and the `assignment` parameter is undocumented anywhere — an agent lacks enough to invoke it fully.
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 only 25%, so the description does some compensating work: it explains the rubric criteria concept, the 3-6 point scale (the `points` parameter), and the 30-submission cap. However it never mentions the `assignment` parameter or that criteria are capped at 8, leaving meaningful gaps at this coverage level.
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 (grade), resource (submissions) and mechanism (rubric you supply) with scope limits (up to 30, parallel). 'A rubric you supply' implicitly distinguishes it from the built-in grade_essay, but no sibling is named, so the differentiation is left to inference.
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 description conveys the usage context (custom rubric, batch of up to 30, 3-6 point scale) but never says when to prefer grade_essay, judge_score, or judge_choice instead, nor any prerequisites. Usage is implied rather than routed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.