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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds value beyond them: the account-link prerequisite for mark schemes, the fact that results arrive paged a few questions at a time, and that mark-scheme rows correspond to the same questions returned. It does not note whether there is a total-count or end-of-paper signal.

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 sentences, front-loaded with the return shape, then pagination, then the optional flag; no filler. The single flaw is the inaccurate 'next_from' label, an error of precision rather than length.

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, and the parenthetical enumeration of returned fields does the job of describing the response. For a read-only, four-parameter retrieval tool this is nearly sufficient; the gaps are how pagination terminates and how large a paper is, both minor.

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 75% schema coverage the schema documents count, paper_id and from_question, and the description adds meaning to include_mark_scheme ('adds the mark-scheme rows for the same questions', needs a linked account) that the bare boolean lacks. The only defect is the mismatched name 'next_from' for the pagination parameter, which slightly muddies rather than clarifies from_question.

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+resource ('An exam.now past paper as structured JSON') and enumerates the payload (metadata, questions, parts, prompts, marks, answer kinds, figure URLs), which lets an agent distinguish it from a single-question fetch. It never explicitly contrasts itself with the sibling get_question, so it falls short of a 5.

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?

Gives real usage context: paginate with the next-page parameter and only set include_mark_scheme when a linked account exists. However, it never says when to prefer this over get_question or find_past_paper, and it refers to 'next_from' while the schema's parameter is named from_question, which can send an agent looking for a nonexistent argument.

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