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

Beyond the read-only and idempotent annotations, it discloses the source, topic tagging, sort order, and fields included in each result, which is especially useful without an output schema. Free-text matching semantics and empty-result or pagination behavior remain unspecified.

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 compact sentences front-load the purpose and ordering, then cover accepted topic forms and returned fields. There is no filler or redundant restatement of the annotations.

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?

For a simple three-parameter read tool, the description and schema together provide the required inputs, accepted topic forms, ordering, result limit constraints, and a useful result summary despite the absence of an output schema. Explicit sibling routing and deeper search semantics would improve selection but are not necessary for a basic correct invocation.

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?

The examples E2.5 and simultaneous equations add concrete guidance beyond the schema's terse topic description. The schema already documents subject_code well, while limit is explained only by its name, default, and numeric bounds rather than by explicit text.

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?

The description identifies the resource, past-paper questions on exam.now, along with the syllabus-topic filter and newest-first ordering, making the list/search purpose clear. Its scope helps separate it from paper-level or single-question siblings, but it does not explicitly contrast it with find_past_paper, get_question, or practise_question.

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?

It provides clear context for discovering questions by syllabus topic and explains that the topic input accepts either a code or words. It does not explicitly say when a sibling is preferable, such as find_past_paper for whole papers or get_question for a known question reference.

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