记录错题

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

With no annotations, the description carries full burden. It discloses immutable numbering, FSRS initialization, and safe retry via idempotency key, which are meaningful behavioral traits. It also cautions against unconfirmed writes. It does not cover duplicate_policy semantics or auth, but overall it adds valuable context beyond a bare create operation.

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 sentences with no redundancy. It front-loads the core action and adds warnings and retry context efficiently. Every sentence earns its place.

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 key aspects: saving confirmed data, immutable ID, FSRS initialization, and safe retry. The output schema exists, so return values need no explanation. It omits duplicate_policy semantics, but the schema's enum and default provide some guidance. Overall, it is complete enough for a create tool with a well-defined schema.

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 0%, so the description must compensate. It explains idempotency_key's role (safe retry) but provides no additional meaning for draft or duplicate_policy. The draft structure is self-evident from the schema, but the description adds little beyond that, leaving a significant gap for two of three 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 clearly states the tool saves a confirmed, transcribed single question, assigns an immutable number, and initializes FSRS. This specific verb+resource combination distinguishes it from siblings like update_problem and search_problems.

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 explicitly warns not to write unconfirmed OCR guesses, providing a clear when-not-to-use condition. It also implies use for confirmed data and mentions idempotency for safe retries. However, it does not name alternative tools or discuss scenario-based selection.

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