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

Adds real context beyond the annotations: a free-tier cap ('free up to a daily limit') and a persistence side effect ('the scored attempt is saved to their History' when signed in), which explains why readOnlyHint is false while destructiveHint stays false. It does not say what happens at the limit or on failure, so it stops short of full behavioral disclosure.

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?

Front-loads the trigger, then the return shape, then the parameter routing, then differentiators — a sensible order with no filler sentences. It is dense and slightly run-on (the fragment 'Free up to a daily limit.'), so it is efficient rather than elegant.

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?

Covers the decisions an agent must make — which exam text qualifies, which of the two optional params to supply, what comes back, quota, account-dependent persistence, and the alternative tool. With an output schema present, it does not need to spell out return structure further, and nothing required for a correct call is missing.

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, but the description adds a constraint the schema does not encode: questionId and prompt are mutually exclusive and exactly one must be supplied. It also ties questionId's provenance to practice_question and prompt's role to off-catalogue prompts, though it leaves exam/taskType semantics to the schema.

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?

Names a specific verb and resource (score a student's essay/summary) and scopes it to named exam families (PTE, IELTS, TOEFL, LanguageCert, MET, CELPIP). It also states the exact return payload — marks out of the task maximum, a score plus one line of feedback per criterion, and top improvements — and explicitly contrasts itself with 'Personalised Tips', so an agent can separate it from nearby scoring options.

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?

Fires on a concrete trigger ('when a student pastes an essay or summary ... and wants a score') and gives the routing rule for the two optional inputs: pass questionId when the text answers one of our questions, otherwise pass the prompt, and pass exactly one. It names the alternative path (Personalised Tips) for sentence-level annotations and verified marks, so when-not-to-use is covered.

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