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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered; the description adds value beyond them by disclosing the return contents (percent, letter on the chosen scale, gap to the next letter, optional chart) and the privacy rule 'Needs only numbers; never ask for names.' Minor gap: it says the chart covers 'every possible number wrong' while the schema caps it at the first 60 rows, an inconsistency an agent could trip over.

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 sentences, front-loaded with the use case, then the return contract, then the exclusions and the input rule. Every sentence carries actionable routing or behavioral information; no filler.

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 an output schema present, 100% parameter coverage, and rich annotations, the description only needs to add routing and behavioral context — which it does. An agent has enough to decide between this and its five siblings and to invoke it without follow-up questions.

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%, so the baseline is 3; the description goes slightly further by framing inputs as 'wrong (or correct)' with a worked example ('7 wrong out of 40'), reinforcing the mutually exclusive wrong/correct choice. It does not add detail on scale, decimals, rounding or custom_cutoffs beyond the schema, so it stays just above baseline.

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 ('percent and letter grade for a test from the number of questions wrong (or correct)') with a concrete example ('7 wrong out of 40'). It also carves out the sibling territory it is not for (final-exam target, weighted categories, GPA, test scores), so an agent can route correctly without opening other schemas.

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?

Explicit when-to-use ('when a student or teacher wants the percent and letter grade...') and explicit when-not ('Do not use it for a final-exam target, weighted categories, GPA or test scores'), which maps cleanly onto final_grade_needed, weighted_grade, gpa_calculator and test_score_calculator. Nothing is left to inference.

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