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

Annotations cover the safety profile (readOnlyHint=true) and openWorldHint=true, so the bar is lower. The description adds meaningful behavior beyond that: the per-kind output shape ('six criteria and a letter grade', 'Reading/Analysis/Writing each 1-4') and the caveat that the SAT source passage is used to check quotations, which is not derivable from the schema.

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 dense paragraph that front-loads the core action before branching into per-kind detail. Sentences are compact and clause-packed, with no filler, though the kind-by-kind enumeration makes it slightly dense on first read.

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 usefully supplies expected outputs per kind. It covers all three modes and the required parameters, leaving only minor gaps (no mention of latency, failure modes, or the 20,000-character input limit).

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?

With 83% schema coverage the baseline is 3, but the description adds real meaning: it explains what each 'kind' enum value does, clarifies that 'level' is essay-only, and ties 'prompt' to the seven Common App prompts with the default of 7. These kind-parameter interactions go beyond the schema's field-level descriptions.

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+resource ('Grade one essay against a built-in rubric') and enumerates the three modes (essay, common-app, sat) with what each produces. The phrase 'built-in rubric' implicitly separates it from the sibling grade_with_rubric, but the sibling is never named, so 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 gives conditional usage for parameters by kind ('pass the prompt number, 1-7', 'pass the source passage to check quotations'), which implies when each mode applies. However, it never states when to choose this tool over grade_with_rubric or the judge_* siblings, and there are no exclusions, so the alternative-selection guidance is missing.

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