record_live_evaluation

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

With no annotations, the description carries the full burden and discloses key behaviors: idempotent return of existing record on duplicate live_session_id, no overwrite, prerequisite of completed status, and that the receipt includes closure progress. It also informs that agent_observation is visible to learners in a collapsible section, which is critical contextual behavior beyond the schema.

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 dense but every sentence adds value: main gate, exception path, prerequisites, idempotency, field guidance, and receipt behavior. It is front-loaded with the core purpose and uses parentheticals to clarify distinctions. No filler or redundant phrases.

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?

Given no output schema, the description covers the return aspect by stating the receipt brings closure progress. It also covers prerequisites, idempotency semantics, and field-level constraints. The tool is complex (8 params, sibling names), and the description provides sufficient context for correct invocation without needing to guess.

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 63%, and the description compensates richly. It explains agent_observation must be a short verdict, not a transcript, and that internal IDs should go to evidence_refs, not the text. It also adds meaning to idempotency_key (use for retries), learner_note (learner-visible, language from locale), and evidence_refs (server-validated against same pair). These explanations go well beyond the schema.

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 uses a specific verb+resource: '写一条 LiveSessionEvaluation' (write a LiveSessionEvaluation), and clearly distinguishes it from record_post_lesson_evaluation by stating this is for a single live_session, not course-level. It also explains the relationship to live_session_complete as the main gate, making the tool's specific role unambiguous.

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 states when to use this tool: as a supplementary channel when the evaluation was missed during closing. It also names the primary flow (live_session_complete with optional evaluation), provides prerequisites (live_session exists with status=completed), and explains idempotent behavior on collision. This is clear, actionable guidance with exclusions.

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