reflect_on_teaching

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

With no annotations provided, the description carries full responsibility and does so extensively. It discloses the silent UI (return only counts, no UI entry), weather_expires_at expiry and the prohibition on learner-profile writes, server-side anchor validation and rejection of non-pair ids, anchor inference fallback with warnings for unanchored reflections, and the closure-progress inclusion in the receipt.

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 flawlessly structured: it front-loads the core action and then details the attribution skeleton, anchor validation, inference logic, and return-receipt behavior. Every sentence contributes a distinct fact about behavior or constraints, with no filler or repetition.

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 highly complex tool with no annotations and no output schema, the description is remarkably complete. It covers the return value (one-line count plus receipt fields like created_refs.anchored_lesson_id and human_note), failure modes (unanchored reflection, pair mismatch), inference precedence order, and closure-progress semantics, leaving very few ambiguities for an agent.

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 56%, and while the description reinforces key parameter relationships (e.g., action_link type-to-ref_id mapping, weather_expires_at requirement), it adds little beyond what the schema's descriptions already state. Several required parameters without schema descriptions (method, rationale, next_action) remain unexplained in both places, making this a minimal-viable rather than compensatory score.

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 explicitly states the tool's purpose ('写一份 TeacherReflection') with clear scope (per-lesson, starting from lesson 3). However, it does not explicitly distinguish itself from sibling tools like record_post_lesson_evaluation or close_lesson_loop, relying instead on its unique attribution-skeleton requirements to imply differentiation.

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 gives clear context: use at the end of each lesson, attach lesson_id, and it explicitly says the receipt includes closure progress so '不用另查状态机' (no need to query the state machine separately), which is a when-not guidance. It does not name alternative tools for similar actions like recording evaluations, limiting it below a 5.

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