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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, and the description adds substantial context beyond them: the return contents, the save_progress_url mechanism, the 20-answer/7-day limits, and the explicit guarantee that nothing is stored unless the user opens the link. This is exactly the kind of behavioral detail annotations cannot convey.

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 front-loaded with purpose and trigger, then moves to return values, then to the token-chaining mechanics. Every sentence earns its place; there is no filler or repetition of schema details.

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 tool with no output schema, the description fully covers return values, the save-token flow, and the conditions for chaining calls. An agent has everything it needs to invoke this tool correctly and to handle the returned data appropriately.

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 coverage is 100%, but the description adds real meaning beyond the schema: it explains how previous_token chains calls, what save_progress_url is for, and gives example choice phrasings. This goes well above the baseline expected for fully covered parameters.

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 states a specific verb ('Grade') and resource ('the user's answer to a practice question from get_practice_question'), making the tool's function immediately clear. It also distinguishes itself from the sibling get_practice_question, which supplies the question rather than grading the answer.

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?

The description explicitly says when to use the tool: when the user replies with their choice, and even gives example phrasings like 'B' or 'I think it is C'. It does not name alternative tools to exclude, but the trigger condition is so specific that no ambiguity remains.

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