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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), and the description adds important behavior: without examLevel it returns available levels and subjects, and math papers live on a separate site. It also instructs the agent to provide the student with the paper's pageUrl. It does not cover pagination or result shape, but those are secondary for a read-only search tool.

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?

The description is compact and front-loads the resource type and source context. The fallback rule and final instruction are clear, though the domain-specific parenthetical adds density without much extra structure.

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?

The description covers the key missing-parameter branch and tells the agent what to hand to the student. It is less complete on year and limit semantics, and without an output schema it only partially characterizes what a normal search returns.

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 description coverage is 0%, so the description must carry parameter meaning. It mentions examLevel and subject behavior, including the special missing-examLevel fallback, but it entirely omits year and limit semantics, leaving half the parameters undocumented.

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 clearly identifies the resource as CKE and mock exam papers with solutions, including the source websites and newest-first ordering. It is distinguishable from siblings like get_exam_task and get_exam_dates, though it does not explicitly name those alternatives for contrast.

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?

Usage is implied for finding exam papers, and the description gives a useful fallback branch when examLevel is missing. However, it does not explicitly say when to use this tool instead of get_exam_task, get_exam_dates, or get_formula_sheets.

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