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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new operational context — 'Works signed out' discloses that no authentication is required, and the fallback listing behavior clarifies runtime semantics. The closing 'Read-only; changes nothing' merely restates the annotations and earns no extra credit.

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 the core purpose, followed by the fallback mode and the environment/safety notes in a logical order. Sentences are dense but each carries information. The final 'Read-only; changes nothing' clause is redundant with the annotations and could be dropped.

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?

There is no output schema, yet the description itemizes what the response covers (math topics by subject, practice set format, problem bank size, official sources including the CA Exam Conversion Sheet). Combined with the auth note, the fallback behavior, and annotations covering safety, nothing an agent needs to invoke this correctly 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?

The single parameter is documented at 100% coverage in the schema, including the 'ca-d2' example, the omit-to-use-saved-grade behavior, and a pointer to save_study_settings. The description adds only a marginal nuance — that with no exam and no saved grade the tool lists the ids — which slightly extends the omission semantics. With the schema doing the heavy lifting, this lands at baseline.

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 — 'describe a California drinking water operator exam (grade)' — and enumerates the concrete content returned (math topics, timed practice set format, problem bank size, official sources). It also names the no-argument fallback behavior (listing every grade with its id), which makes the tool's dual mode unmistakable and separates it from siblings like start_mock_exam or practice_questions.

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 an explicit use condition: call with no exam 'before the user has chosen a grade' to enumerate available grades. That is clear when-to-use guidance. It does not name sibling alternatives (e.g., practice_questions or get_study_plan) as explicit exclusions, so it falls short of a full when/when-not/alternatives statement.

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