record_practice

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

Adds real behavioral context beyond annotations: it declines to grade or judge mastery, forbids inferring 'independent' assistance from a correct answer, preserves source_revision/snapshot history, and states that conflicting duplicate submissions are rejected rather than overwritten. Note the conditional idempotency via attempt_key sits in tension with idempotentHint=false, though it is scoped to matching keys so not a hard contradiction.

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?

A dense but front-loaded paragraph that leads with purpose before parameter guidance, with each clause carrying new information. It runs slightly long and packs many constraints into one block, but there is little filler.

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?

Output schema exists so return values need not be described, and annotations cover the safety profile. For a 7-parameter mutation tool the critical semantics (assistance, attempt_key, exercise_index) are covered, though required fields expected_revision and response are never addressed.

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 schema description coverage at 0%, the description must compensate and largely does: it explains exercise_index vs practice_kind, the four assistance enum values and their non-inferability, and the attempt_key retry/dedup contract. It leaves response, record_id, and expected_revision semantics unexplained, so it is strong but not complete.

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 ('记录...再次作答') and immediately bounds the scope by declaring what it does NOT do ('不自动判分或判定掌握'), which cleanly separates it from grading-oriented siblings like check_exercise and review_practice_attempt.

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 concrete when-to conditions: default exercise requires a 0-based exercise_index while 'original' passes none, and recommends generating attempt_key per attempt with same-key retries for idempotency. It does not explicitly name an alternative sibling or a when-not-to-use-this condition, so 4 rather than 5.

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