record_post_lesson_evaluation

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

With no annotations, the description carries the full burden and does so thoroughly: it reveals update-in-place behavior on duplicate (pair_id, lesson_id), rejection of all-default payloads, the three-part structure of agent_observation, the three-channel rule for internal IDs (only in evidence_refs), and receipt behavior including update-not-create and progress. No contradictions with annotations because none are present.

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 a dense paragraph of operational rules with no filler; every clause contributes to correct usage. It could be more scannable with bullet points, but the natural-language flow remains efficient and information-dense, earning a 4.

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 13 parameters, nested objects, uniqueness constraints, and detailed validation rules, the description covers purpose, timing, content restrictions (one-decision principle, no restating exercises), rejection criteria, idempotency, update semantics, and receipt behavior. It also references the spec for threshold details, making it effectively complete for an agent to select and invoke it correctly.

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 description adds significant meaning beyond the schema by explaining the three-channel system (learner_note, evidence_refs, agent_observation), the rule that agent_observation must avoid machine terms and internal IDs, and the rejection condition covering seven parameters. However, several numeric fields (e.g., concepts_touched, duration_minutes) still lack explicit semantic clarification, so 4 rather than 5.

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 '写一条 PostLessonEvaluation' (write one PostLessonEvaluation) and specifies it is a pure fact-layer record written at the end of every lesson. It differentiates from siblings like record_live_evaluation and grade_exercise by explicitly stating exercise judgments belong to grade_exercise and that live comparisons form part of agent_observation.

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 provides explicit timing ('每节课末尾都写' — write at the end of every lesson), a directive to avoid restating exercise judgments (pointing to grade_exercise), and a reference to the three-lesson threshold rule in TEACHING-SPEC §4.3. It also states the receipt carries closed-loop progress so state-machine queries are unnecessary, implicitly guiding against using sibling tools.

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