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

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description adds genuinely new behavior: the no-questionNumber list-return mode, duplicate-number handling via position, LaTeX delimiters ($ vs $$), fully-qualified image URLs, and the instruction to surface pageUrl to the student. This is context an agent could not infer from structured fields.

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-loaded with what the tool returns, followed by the conditional-return rule and the format/usage notes. Every sentence carries actionable information; nothing is redundant with the schema or 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?

No output schema exists, so the description carries the burden of describing return contents, and it does: task statement, step-by-step solution, final answer, LaTeX-delimited formulas, absolute image URLs, plus the list mode. An agent has everything needed to call it and interpret the result.

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 50% schema coverage, the description compensates by explaining where slug originates and how questionNumber versus position interact, going beyond the schema's own notes. examLevel's four enum values are self-documenting in the schema, so their absence from the description is minor.

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: fetch a single math exam task (identified by slug from search_exam_papers) including the statement, step-by-step solution and final answer. It is clearly distinct from the sibling search_exam_papers, which produces the slug this tool consumes.

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?

Explicitly says the slug comes from search_exam_papers, and explains the important branch: without questionNumber it returns the task list, and when numbers repeat you must pass position from that list. No explicit 'when not to use' or exclusion statements, but the retrieval workflow is unambiguous.

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